Large Language Models (LLMs) Training in Varna

This instructor-led, live training in Varna (online or onsite) is designed for senior management professionals who aim to understand LLMs, explore their potential impact on business operations, and evaluate practical uses of AI tools such as ChatGPT, Microsoft Copilot, or Grok for real-world tasks like content creation, data summarization, and decision support.

Upon completion of this training, participants will be able to:

• Comprehend the nature of LLMs and the functionality of tools like ChatGPT and Copilot.
• Apply prompt techniques to obtain practical and reliable results from LLMs.
• Assess real-world use cases, including email drafting, document summarization, and productivity automation.
• Identify investment opportunities and strategic applications for AI adoption.

This instructor-led, live training in Varna (online or onsite) is designed for senior management teams seeking to understand the strategic value of LLMs and enterprise AI tools. Participants will explore how to integrate these tools into high-level workflows, draft better prompts, and evaluate opportunities for increased productivity and ROI through AI adoption.

By the end of this training, participants will be able to:

• Understand how LLMs function and how tools like ChatGPT and Copilot apply them.
• Use prompt-based interactions to automate and accelerate tasks.
• Apply AI tools to real scenarios such as email drafting, report summarization, and agreement review.
• Evaluate strategic benefits, limitations, and licensing considerations for LLM adoption.

This instructor-led, live training in Varna (available online or on-site) is designed for intermediate to advanced AI researchers, data scientists, and developers who wish to master the understanding, fine-tuning, and implementation of Meta AI's Large Language Models for diverse NLP applications.

By the conclusion of this training, participants will be able to:

• Understand the underlying architecture and functionality of Meta AI's Large Language Models.
• Set up and fine-tune Meta AI LLMs for specific practical applications.
• Develop LLM-based solutions such as chatbots, text summarization tools, and sentiment analysis systems.
• Optimize and efficiently deploy large language models.

This live, instructor-led training, conducted in Varna (online or onsite), targets intermediate-level AI professionals, business analysts, and technology leaders eager to master generative AI principles and LLM applications in business. The curriculum covers transformer architecture, prompt engineering, and the ethical aspects of deploying these models for real-world problem solving.

Upon completion, participants will be able to:

• Comprehend the core principles of generative AI and large language models.
• Implement and fine-tune LLMs for specific business applications.
• Apply prompt engineering techniques to optimize model outputs.
• Recognize ethical considerations and manage risks during LLM deployment.

This instructor-led, live training in Varna (online or onsite) is designed for intermediate-level AI professionals, ethicists, data scientists, engineers, as well as policy makers and stakeholders seeking to understand and navigate the ethical landscape surrounding LLMs.

Upon completion of this training, participants will be able to:

• Identify ethical issues and challenges associated with LLMs.
• Apply ethical frameworks and principles to LLM deployment.
• Assess the societal impact of LLMs and mitigate potential risks.
• Develop strategies for responsible AI development and usage.

This instructor-led, live training in Varna (online or onsite) is designed for intermediate-level NLP practitioners, data scientists, content creators, translators, and global businesses seeking to utilize LLMs for language translation and multilingual content creation.

By the end of this training, participants will be able to:

• Understand the core principles of cross-lingual learning and translation with LLMs.
• Implement LLMs for translating content across various languages.
• Create and manage multilingual datasets for LLM training.
• Develop strategies to maintain consistency and quality in translation.

This instructor-led, live training in Varna (online or onsite) is aimed at intermediate-level financial analysts, data scientists, and investment professionals who wish to leverage LLMs for financial market analysis and prediction.

By the end of this training, participants will be able to:

• Understand the application of LLMs in financial market analysis.
• Use LLMs to process financial news, reports, and data for market insights.
• Develop predictive models for stock prices, market trends, and economic indicators.
• Integrate LLM insights into investment decision-making processes.

This instructor-led, live training in Varna (online or onsite) is aimed at intermediate-level environmental scientists and researchers, data analysts, and policy makers and environmental advocates who wish to use LLMs for environmental modeling and analysis.

By the end of this training, participants will be able to:

• Understand the application of LLMs in environmental science.
• Utilize LLMs to analyze and model environmental data.
• Interpret LLM outputs for environmental impact assessments.
• Communicate findings effectively to inform policy and conservation efforts.

This instructor-led, live training in Varna (online or onsite) is designed for intermediate-level VR and AR developers, game designers, and AI engineers who want to incorporate LLMs into VR and AR applications to create more engaging and responsive environments.

By the end of this training, participants will be able to:

• Grasp the role of LLMs in crafting immersive VR and AR experiences.
• Build VR and AR applications that leverage LLMs for interactive dialogues and content creation.
• Integrate LLMs with VR and AR development tools to boost user engagement.
• Apply best practices for designing AI-driven narratives and interactions within virtual spaces.

This instructor-led, live training in Varna (online or on-site) is designed for intermediate-level data scientists, machine learning engineers, and software developers interested in applying Large Language Models (LLMs) to multimodal data for advanced AI applications.

By the end of this training, participants will be able to:

• Grasp the core principles of multimodal learning using LLMs.
• Deploy LLMs to process and analyze text, image, and audio inputs.
• Build applications that capitalize on the benefits of integrated multimodal data.
• Assess the performance of multimodal LLM architectures.

This instructor-led, live training in Varna (online or onsite) targets intermediate-level cybersecurity specialists and data scientists who aim to leverage LLMs to strengthen security defenses and enhance threat intelligence capabilities.

Upon completion of this training, participants will be able to:

• Grasp the significance of LLMs within the cybersecurity landscape.
• Deploy LLMs for the purpose of detecting and analyzing threats.
• Apply LLMs to streamline security automation and incident response.
• Seamlessly integrate LLMs into current security infrastructure.

This instructor-led, live training in Varna (online or onsite) is designed for intermediate-level data scientists and business analysts who want to leverage large language models (LLMs) to predict trends and behaviors across various industries.

By the end of this training, participants will be able to:

• Grasp the fundamentals of LLMs and their significance in predictive analytics.
• Deploy LLMs to analyze and forecast data within diverse industry sectors.
• Assess the effectiveness of predictive models constructed using LLMs.
• Seamlessly integrate LLMs into current data processing pipelines.

This instructor-led, live training in Varna (online or on-site) targets intermediate-level data scientists aiming to develop a comprehensive understanding and practical skills in both Large Language Models (LLMs) and Reinforcement Learning (RL).

By the conclusion of this training, participants will be able to:

• Understand the components and functionality of transformer models.
• Optimize and fine-tune LLMs for specific tasks and applications.
• Understand the core principles and methodologies of reinforcement learning.
• Learn how reinforcement learning techniques can enhance the performance of LLMs.

This instructor-led, live training in Varna (online or onsite) is aimed at intermediate-level content creators, marketers, and educational technologists who wish to harness the power of LLMs for generating high-quality, diverse, and engaging content across various domains.

By the end of this training, participants will be able to:

• Understand the capabilities of LLMs and their application in content generation.
• Set up and use LLMs for generating various types of content.
• Apply best practices for prompting and fine-tuning LLMs to produce desired outputs.
• Evaluate the quality of AI-generated content and refine it for specific audiences.
• Explore advanced techniques for creative and multi-modal content generation with LLMs.

This instructor-led, live training in Varna (online or onsite) is designed for educators, EdTech professionals, and researchers of varying experience levels who aim to leverage LLMs to create personalized educational experiences.

Upon completion of this training, participants will be able to:

• Comprehend the architecture and capabilities of LLMs.
• Identify opportunities for personalizing educational content using LLMs.
• Design adaptive learning platforms that employ LLMs for content personalization.
• Implement LLM-driven strategies to enhance student engagement and learning outcomes.
• Evaluate the effectiveness of LLMs in educational settings and make data-driven decisions for

This instructor-led, live training in Varna (online or onsite) targets intermediate-level machine learning practitioners and AI developers who wish to fine-tune and deploy open-weight models such as LLaMA, Mistral, and Qwen for specific business or internal applications.

Upon completion of this training, participants will be able to:

• Understand the ecosystem and distinctions among open-source LLMs.
• Prepare datasets and fine-tuning configurations for models like LLaMA, Mistral, and Qwen.
• Execute fine-tuning pipelines using Hugging Face Transformers and PEFT.
• Evaluate, save, and deploy fine-tuned models in secure environments.

This instructor-led, live training in Varna (online or onsite) targets beginner to intermediate software developers and data scientists looking to implement LLMs within speech recognition and synthesis systems.

Upon completion of this training, participants will be able to:

• Comprehend the role of LLMs in speech technologies.
• Implement LLMs to achieve accurate speech recognition and natural-sounding speech synthesis.
• Integrate LLMs with speech recognition engines and speech synthesizers.
• Evaluate and enhance the performance of speech systems utilizing LLMs.
• Stay abreast of current trends and future directions in speech technologies.

This instructor-led live training in Varna (online or onsite) is designed for beginner to intermediate customer support and IT professionals who aim to utilize LLMs to develop responsive and intelligent chatbots for customer service.

By the end of this training, participants will be able to:

• Comprehend the core principles and architecture of Large Language Models (LLMs).
• Design and integrate LLMs into customer support infrastructures.
• Improve the responsiveness and overall user experience of chatbot interactions.
• Navigate ethical implications and ensure adherence to industry standards.
• Deploy and sustain LLM-driven chatbots for practical, real-world use cases.

This guided, live training session Varna (online or on-site) is designed for data scientists and AI engineers at an intermediate level who seek to fine-tune large language models in a more cost-effective and efficient manner using techniques like LoRA, Adapter Tuning, and Prefix Tuning.

Upon completion of this training, participants will be capable of:

• Comprehending the theoretical foundations underlying parameter-efficient fine-tuning methodologies.
• Implementing LoRA, Adapter Tuning, and Prefix Tuning utilizing the Hugging Face PEFT library.
• Evaluating the performance and cost trade-offs between PEFT methods and full fine-tuning.
• Deploying and scaling fine-tuned LLMs while minimizing computational and storage demands.

This live, instructor-led training Varna (online or onsite) targets intermediate to advanced machine learning engineers, AI developers, and data scientists eager to master the use of QLoRA for efficiently fine-tuning large models for specific tasks and customizations.

By the conclusion of this training, participants will be able to:

• Comprehend the theory behind QLoRA and quantization techniques for LLMs.
• Implement QLoRA in the fine-tuning of large language models for domain-specific applications.
• Optimize fine-tuning performance on limited computational resources using quantization.
• Deploy and evaluate fine-tuned models in real-world applications efficiently.

This instructor-led live training, available online or onsite, is tailored for intermediate-level data and marketing professionals who aim to utilize Large Language Models (LLMs) to analyze and interpret public sentiment from diverse text sources such as social media posts, product reviews, and customer feedback.

By the end of this training, participants will be able to:

• Understand the principles of sentiment analysis and its application using LLMs.
• Preprocess and prepare datasets for sentiment analysis.
• Train and fine-tune LLMs to accurately reflect sentiment in text.
• Analyze sentiment in real-time from social media and other text sources.
• Integrate sentiment analysis findings into business strategies and decision-making processes.

This instructor-led, live training, conducted Varna (online or onsite), is designed for intermediate-level software developers and technical writers seeking to utilize LLMs to streamline their coding processes and create detailed, comprehensive documentation.

By the conclusion of this training, participants will be able to:

• Understand the role of LLMs in automating code generation and software documentation.
• Utilize LLMs to create accurate and efficient code snippets and documentation.
• Integrate LLMs into their software development lifecycle for enhanced productivity.
• Maintain high-quality documentation standards using automated tools.
• Address ethical considerations and best practices for using AI in software development.

This instructor-led live training in Varna (online or onsite) targets intermediate-level business professionals and data analysts eager to use LLMs for extracting valuable business insights.

By the end of this training, participants will be able to:

• Understand the fundamentals and applications of LLMs in the context of business intelligence.
• Apply LLMs to analyze large datasets and extract meaningful insights.
• Integrate LLM-driven analytics into strategic business decision-making processes.
• Evaluate the ethical considerations and best practices for using LLMs in business.
• Anticipate future trends in AI and prepare for the evolving landscape of business intelligence.

This instructor-led live training in Varna (online or onsite) targets intermediate to advanced developers and data scientists who wish to master LlamaIndex for developing innovative LLM-powered applications.

By the end of this training, participants will be able to:

• Set up and configure LlamaIndex for use with LLMs.
• Index and query custom datasets using LlamaIndex to enhance LLM functionality.
• Design and develop sophisticated applications that utilize LlamaIndex and LLMs.
• Understand and apply best practices for working with LLMs and LlamaIndex.
• Navigate the ethical considerations involved in deploying LLM-powered applications.

This instructor-led, live training in Varna (online or onsite) is aimed at intermediate-level AI researchers, machine learning professionals, and data scientists who wish to use LlamaIndex to enhance the capabilities of AI models, making them more accurate and reliable for various applications.

By the end of this training, participants will be able to:

• Understand the principles and components of LlamaIndex.
• Ingest and structure data for use with LLMs.
• Implement context augmentation to improve AI model performance.
• Integrate LlamaIndex into existing AI systems and workflows.

This instructor-led, live training in Varna (online or onsite) is designed for intermediate-level professionals seeking to utilize prompt engineering and few-shot learning to optimize LLM performance for real-world applications.

By the conclusion of this training, participants will be capable of:

• Understanding the core principles of prompt engineering and few-shot learning.
• Designing effective prompts for various NLP tasks.
• Leveraging few-shot techniques to adapt LLMs with minimal data.
• Optimizing LLM performance for practical applications.

LangGraph serves as a framework designed to build stateful, multi-agent LLM applications through composable graphs that maintain persistent state and offer precise control over execution.

This instructor-led training, available either online or on-site, targets intermediate to advanced professionals aiming to design, implement, and manage LangGraph-based legal solutions while ensuring necessary compliance, traceability, and governance controls.

Upon completion of this training, participants will be equipped to:

• Create legal-specific LangGraph workflows that maintain auditability and compliance.
• Incorporate legal ontologies and document standards into graph states and processing.
• Implement guardrails, human-in-the-loop approvals, and traceable decision pathways.
• Deploy, monitor, and maintain LangGraph services in production environments with effective observability and cost management.

Course Format

• Interactive lectures and discussions.
• Extensive exercises and practical applications.
• Hands-on implementation within a live laboratory environment.

Customization Options

• For tailored training on this subject, please contact us to arrange your specific requirements.

Delivered as instructor-led live training, available either online or onsite, this course targets advanced engineers, AI specialists, and localization leads who want to implement large language model (LLM) systems for automated translation, quality evaluation, and corporate governance.

Upon completion of this training, participants will be able to:

• Construct enterprise-grade LLM localization pipelines that integrate both open-source and proprietary models.
• Deploy automated QA workflows and define quality metrics to ensure translation consistency.
• Set up governance and approval structures for the production of multilingual content.
• Launch scalable, auditable LLM-based localization systems within secure infrastructure.

AI for SQL involves applying artificial intelligence and large language models (LLMs) to automate, optimize, and improve the generation, execution, and interpretation of SQL queries within enterprise data environments.

This instructor-led, live training (available online or on-site) targets intermediate-level data engineers and technical leads seeking to integrate AI capabilities into their SQL workflows. The course enables natural language querying, intelligent optimization, and automated data analysis.

Upon completing this training, participants will be able to:

• Integrate LLMs such as GPT, DeepSeek, LLaMA, Qwen, and Mistral into SQL environments.
• Develop natural-language-to-SQL pipelines for conversational data access.
• Implement AI-driven query optimization and error detection.
• Design secure, auditable AI-SQL workflows suitable for enterprise use.

Format of the Course

• Interactive lecture and discussion.
• Extensive exercises and practice.
• Hands-on implementation in a live-lab environment.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

LangGraph serves as a framework for constructing stateful, multi-agent LLM applications that operate as composable graphs with persistent state and precise control over execution.

This instructor-led, live training (available online or onsite) targets intermediate to advanced professionals aiming to design, implement, and manage LangGraph-based finance solutions that adhere to proper governance, observability, and compliance standards.

Upon completion of this training, participants will be capable of:

• Designing finance-specific LangGraph workflows that align with regulatory and audit requirements.
• Integrating financial data standards and ontologies into graph states and tooling.
• Implementing reliability, safety, and human-in-the-loop controls for critical processes.
• Deploying, monitoring, and optimizing LangGraph systems to ensure performance, cost efficiency, and SLA compliance.

Course Format

• Interactive lectures and discussions.
• Extensive exercises and practical sessions.
• Hands-on implementation within a live-lab environment.

Course Customization Options

• To request customized training for this course, please contact us to arrange details.

Vertex AI offers robust tools for constructing multimodal LLM workflows that seamlessly combine text, audio, and visual data into a unified pipeline. Supported by long context window capabilities and Gemini API parameters, it facilitates the development of sophisticated applications focused on planning, reasoning, and cross-modal intelligence.

This guided, live training session (available online or on-site) is designed for intermediate to advanced professionals looking to design, build, and optimize multimodal AI workflows within Vertex AI.

Upon completion of this training, participants will be equipped to:

• Utilize Gemini models to handle multimodal inputs and outputs.
• Establish long-context workflows tailored for complex reasoning tasks.
• Architect pipelines that integrate the analysis of text, audio, and images.
• Fine-tune Gemini API parameters to enhance performance and cost-effectiveness.

Course Format

• Engaging lectures paired with interactive discussions.
• Practical labs focusing on multimodal workflows.
• Project-based exercises applying multimodal use cases.

Customization Options

• For requests regarding customized training for this course, please reach out to us to make arrangements.

LangGraph facilitates stateful, multi-actor workflows driven by Large Language Models (LLMs), offering precise control over execution paths and state persistence. In the healthcare sector, these capabilities are essential for ensuring compliance, enabling interoperability, and developing decision-support systems that seamlessly align with clinical workflows.

This instructor-led live training (available online or onsite) targets intermediate to advanced professionals aiming to design, implement, and manage LangGraph-based healthcare solutions while navigating regulatory, ethical, and operational challenges.

Upon completion of this training, participants will be able to:

• Design healthcare-specific LangGraph workflows with compliance and auditability as key considerations.
• Integrate LangGraph applications with medical ontologies and standards, including FHIR, SNOMED CT, and ICD.
• Apply best practices for reliability, traceability, and explainability in sensitive environments.
• Deploy, monitor, and validate LangGraph applications within healthcare production settings.

Course Format

• Interactive lectures and discussions.
• Hands-on exercises featuring real-world case studies.
• Implementation practice in a live-lab environment.

Course Customization Options

• To request customized training for this course, please contact us to make arrangements.

This instructor-led live training (online or onsite) is designed for intermediate-level AI developers and localization engineers seeking to build scalable, automated translation pipelines using proprietary and open-source LLMs.

By the end of this course, participants will be able to:

• Design and deploy translation workflows using modern LLM frameworks and APIs.
• Integrate open-source and commercial models into scalable translation systems.
• Optimize translation quality through fine-tuning, prompt engineering, and automation.
• Implement cost-efficient and compliant translation infrastructure for enterprise environments.

LangGraph is a framework designed for constructing stateful, multi-agent LLM applications as composable graphs, featuring persistent state and precise execution control.

This instructor-led live training, available online or onsite, targets advanced AI platform engineers, DevOps professionals specializing in AI, and ML architects who aim to optimize, debug, monitor, and manage production-grade LangGraph systems.

By the conclusion of this training, participants will be able to:

• Design and optimize complex LangGraph topologies to enhance speed, reduce costs, and improve scalability.
• Ensure reliability through retries, timeouts, idempotency, and checkpoint-based recovery mechanisms.
• Debug and trace graph executions, inspect state changes, and systematically reproduce production issues.
• Instrument graphs with logs, metrics, and traces; deploy them to production; and monitor SLAs and costs.

Format of the Course

• Interactive lectures and discussions.
• Extensive exercises and practical practice.
• Hands-on implementation in a live-lab environment.

Course Customization Options

• To request customized training for this course, please contact us to arrange it.

This instructor-led live training, delivered Varna (online or onsite), targets intermediate-level developers interested in mastering the application of generative AI and LLMs for diverse tasks and industries.

By the conclusion of this session, participants will be able to:

• Clearly define generative AI and explain its operational principles.
• Describe the transformer architecture driving LLMs.
• Apply empirical scaling laws to optimize LLMs for various tasks and constraints.
• Implement state-of-the-art tools and methods for training, fine-tuning, and deploying LLMs.
• Discuss the broader opportunities and risks generative AI presents to society and business.

Large Language Models (LLMs) and autonomous agent frameworks, such as AutoGen and CrewAI, are transforming the way DevOps teams automate tasks like change tracking, test generation, and alert triage by emulating human-like collaboration and decision-making processes.

This instructor-led live training, available online or on-site, is designed for advanced engineers who want to design and implement DevOps automation workflows driven by large language models (LLMs) and multi-agent systems.

Upon completion of this training, participants will be able to:

• Integrate LLM-based agents into CI/CD workflows to enable intelligent automation.
• Automate test generation, commit analysis, and change summaries using agents.
• Coordinate multiple agents for alert triage, response generation, and DevOps recommendations.
• Construct secure and maintainable agent-powered workflows utilizing open-source frameworks.

Course Format

• Interactive lectures and discussions.
• Extensive exercises and practical application.
• Hands-on implementation within a live-lab environment.

Customization Options

• To request customized training for this course, please contact us to make arrangements.

Postgres is an advanced open-source relational database that can serve as a foundation for AI-powered systems and data intelligence applications.

This instructor-led, live training (online or onsite) is aimed at intermediate-level database professionals and developers who wish to integrate, manage, and optimize AI capabilities directly within Postgres.

By the end of this training, participants will be able to:

• Set up and configure Postgres extensions for AI workloads.
• Implement embeddings and similarity search using pgvector.
• Integrate open source and proprietary LLMs with Postgres for real-time insights.
• Optimize Postgres for handling AI-driven queries and workflows.

Format of the Course

• Interactive lecture and discussion.
• Lots of exercises and practice.
• Hands-on implementation in a live-lab environment.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

This instructor-led, live training in Varna (online or onsite) is aimed at intermediate to advanced AI developers, architects, and product managers who wish to identify and mitigate risks associated with LLM-powered applications, including prompt injection, data leakage, and unfiltered output, while incorporating security controls like input validation, human-in-the-loop oversight, and output guardrails.

By the end of this training, participants will be able to:

• Understand the core vulnerabilities of LLM-based systems.
• Apply secure design principles to LLM app architecture.
• Use tools such as Guardrails AI and LangChain for validation, filtering, and safety.
• Integrate techniques like sandboxing, red teaming, and human-in-the-loop review into production-grade pipelines.

LangGraph is a graph-based orchestration framework designed to facilitate conditional, multi-step workflows involving Large Language Models (LLMs) and various tools. It is particularly well-suited for automating and personalizing content pipelines.

This instructor-led live training, available both online and onsite, targets intermediate-level marketers, content strategists, and automation developers looking to build dynamic, branching email campaigns and content generation pipelines using LangGraph.

Upon completion of this training, participants will be equipped to:

• Create graph-structured workflows for emails and content that incorporate conditional logic.
• Connect LLMs, APIs, and data sources to enable automated personalization.
• Manage state, memory, and context throughout multi-step campaigns.
• Assess, monitor, and optimize the performance and delivery results of workflows.

Course Format

• Interactive lectures accompanied by group discussions.
• Practical labs focused on implementing email workflows and content pipelines.
• Scenario-based exercises covering personalization, segmentation, and branching logic.

Course Customization Options

• To arrange a customized version of this training, please contact us.

This instructor-led, live training in Varna (online or onsite) is designed for intermediate to advanced professionals looking to tailor pre-trained models for particular tasks and datasets.

Upon completion of this training, participants will be able to:

• Grasp the principles of customization and its real-world applications.
• Prepare datasets specifically for customizing pre-trained models.
• Customize Large Language Models (LLMs) for NLP tasks.
• Enhance model performance and tackle common challenges.

LangGraph is a framework designed for composing graph-structured workflows involving LLMs, enabling features such as branching, tool usage, memory management, and controllable execution.

This instructor-led, live training (available online or onsite) targets intermediate-level engineers and product teams looking to integrate LangGraph’s graph logic with LLM agent loops to create dynamic, context-aware applications. Examples include customer support agents, decision trees, and information retrieval systems.

Upon completing this training, participants will be capable of:

• Designing graph-based workflows that effectively coordinate LLM agents, tools, and memory.
• Implementing conditional routing, retries, and fallback mechanisms to ensure robust execution.
• Integrating retrieval mechanisms, APIs, and structured outputs into agent loops.
• Evaluating, monitoring, and hardening agent behavior to enhance reliability and safety.

Course Format

• Interactive lectures and facilitated discussions.
• Guided labs and code walkthroughs within a sandbox environment.
• Scenario-based design exercises and peer reviews.

Course Customization Options

• To request a customized training session for this course, please contact us to arrange.

The course "LLMs for Code Comprehension, Refactoring, and Documentation" is a technical program dedicated to leveraging large language models (LLMs) to enhance code quality, minimize technical debt, and streamline documentation processes within software development teams.

This instructor-led live training, available either online or on-site, targets intermediate to advanced software professionals who aim to utilize LLMs, such as GPT, to more effectively analyze, refactor, and document complex or legacy codebases.

Upon completion of this training, participants will be equipped to:

• Employ LLMs to elucidate code structures, dependencies, and logic within unfamiliar repositories.
• Recognize and refactor anti-patterns to enhance code readability.
• Automate the creation and maintenance of inline comments, README files, and API documentation.
• Seamlessly integrate LLM-derived insights into current CI/CD pipelines and code review workflows.

Course Format

• Interactive lectures and discussions.
• Extensive exercises and practical application.
• Hands-on implementation within a live-lab environment.

Customization Options for the Course

• To arrange customized training for this course, please contact us.

This instructor-led, live training in Bulgaria (online or onsite) is aimed at intermediate-level data scientists, AI developers, and AI enthusiasts who wish to use LLMs to perform various NLP tasks and create novel and diverse content for different purposes.

By the end of this training, participants will be able to:

• Establish a development environment with LLMs and essential tools.
• Expertly perform NLU and NLI tasks with LLMs.
• Extract, infer, and utilize knowledge graphs effectively.
• Generate and manage dialogues using LLMs for conversational applications.
• Evaluate content quality and diversity generated by LLMs and generative AI.
• Apply ethical principles, ensuring fairness and responsible use of LLMs.

LangGraph is a specialized framework designed for constructing LLM applications with a graph-based architecture. It facilitates advanced capabilities such as planning, branching logic, tool utilization, memory management, and controllable execution flows.

This instructor-led live training, available both online and onsite, is tailored for beginner-level developers, prompt engineers, and data practitioners aiming to design and implement reliable, multi-step LLM workflows using LangGraph.

Upon completion of this training, participants will be equipped to:

• Articulate core LangGraph concepts, including nodes, edges, and state, and understand appropriate use cases.
• Construct prompt chains that support branching, tool invocation, and persistent memory.
• Integrate retrieval mechanisms and external APIs into graph-based workflows.
• Test, debug, and evaluate LangGraph applications to ensure reliability and safety.

Course Format

• Interactive lectures coupled with facilitated discussions.
• Guided laboratory exercises and code walkthroughs within a sandbox environment.
• Scenario-based exercises focusing on design, testing, and evaluation strategies.

Customization Options

• For requests regarding customized training for this course, please contact us to arrange suitable arrangements.

This instructor-led, live training in Varna (online or onsite) targets beginner to intermediate developers looking to utilize Large Language Models for various natural language tasks.

By the end of this training, participants will be able to:

• Set up a development environment that includes a popular LLM.
• Create a basic LLM and fine-tune it on a custom dataset.
• Use LLMs for different natural language tasks such as text summarization, question answering, text generation, and more.
• Debug and evaluate LLMs using tools such as TensorBoard, PyTorch Lightning, and Hugging Face Datasets.

This instructor-led, live training in Varna (online or on-site) is designed for intermediate-level engineers and architects who wish to use Tencent Hunyuan to deploy large and MoE models with lower latency, higher throughput, and improved cost control.

By the end of this training, participants will be able to: explain Hunyuan production deployment patterns, optimize inference performance, implement batching and quantization strategies, and plan scalable serving operations.

This instructor-led, live training Varna (available online or onsite) targets intermediate-level developers, technical product teams, and AI practitioners aiming to utilize Hunyuan models for developing multimodal applications involving image, 3D, and video generation and distribution.

By the conclusion of this training, participants will be capable of: establishing prompt-driven workflows, generating and evaluating multimodal assets, serving outputs via applications or APIs, and linking Hunyuan capabilities to enterprise product infrastructures.

This instructor-led, live training in Varna (online or onsite) is designed for AI professionals at the beginner, intermediate, or advanced levels who wish to use MCP to connect AI assistants with external tools, data, and enterprise services.

By the end of this training, participants will be able to explain MCP concepts, identify key architectural components, set up a basic integration, and apply security best practices.

This instructor-led, live training in Varna (online or onsite) is aimed at intermediate-level enterprise architects who wish to use Model Context Protocol to design secure, scalable, and governable agent integration platforms for enterprise environments.

By the end of this training, participants will be able to: explain MCP architecture and enterprise patterns, design secure integration platforms, apply governance and access controls, and evaluate deployment and scaling options.

This instructor-led, live training in Varna (online or onsite) is aimed at intermediate-level developers, architects, and platform engineers who wish to use MCP to build reliable servers and clients for enterprise deployment and operations.

By the end of this training, participants will be able to: explain MCP architecture in practice, build production-ready integrations, deploy and observe MCP services, and apply versioning, resilience, and support patterns.

This instructor-led, live training in Varna (online or onsite) is designed for intermediate-level IT leaders, compliance professionals, security teams, and enterprise architects. It focuses on using sovereign AI principles and governance practices to design AI environments that protect sensitive data, support localization requirements, and reduce vendor lock-in.

By the end of this training, participants will be able to explain sovereign AI concepts, evaluate hosting and governance options, define controls for prompts and logs, and create a practical adoption roadmap.