LLMs for IT Professionals: Building, Fine-tuning, and Deploying

Course overview

• Hands-On LLM Development: Gain practical expertise in developing and deploying Large Language Model (LLM)-based applications, including working with transformers, datasets, and Python-based AI models.
• Fine-Tuning and Integration: Master techniques for fine-tuning LLMs, optimizing performance, and integrating them into applications through APIs and custom solutions.
• Deployment and Monitoring: Explore strategies for secure deployment, testing, and monitoring LLMs in production environments, ensuring robust and reliable performance.
• Ethical and Responsible AI: Address ethical considerations in AI, including bias detection and mitigation, while applying responsible AI practices.

Modules

• Module 1: Introduction and Fundamentals
  • Understand transformer architecture, including key components like attention mechanisms and encoder-decoder structures.
  • Explore popular transformer models such as BERT, GPT, and T5, along with real-world applications.
  • Learn the capabilities, training methodologies, and differences between LLMs and traditional ML/NLP models.
  • Hands-on assignment: Use pre-trained LLMs for tasks like text generation, summarization, and sentiment analysis.
• Module 2: Building and Fine-Tuning LLMs
  • Learn to source, clean, and preprocess datasets, applying tokenization, padding, and batch processing techniques.
  • Fine-tune LLMs on custom datasets and optimize performance using advanced architectures like Adapter layers, LoRA, and QLoRA.
  • Hands-on assignment: Fine-tune an LLM and address common optimization challenges
• Module 3: Leveraging LLMs Through APIs and Integration
  • Access and utilize API-based LLM services, understanding authentication, rate limits, and usage costs.
  • Build LLM-powered applications like chatbots and summarizers, leveraging evaluation metrics like BLEU, ROUGE, and Perplexity.
  • Integrate LLMs into backend and frontend applications, ensuring secure API usage and data privacy.
  • Hands-on assignment: Create a functional application using an LLM API and deploy it in an end-to-end pipeline.
• Module 4: Utilization of RAG and MCP
  • Understand the architecture and use-cases of Retrieval-Augmented Generation (RAG), including how it combines knowledge retrieval with LLM-based generation.
  • Learn to set up and integrate RAG frameworks with existing LLMs to enhance factual accuracy and reduce hallucinations.
  • Explore Memory-Contextual Prompting (MCP) techniques to provide dynamic, personalized responses in applications like chatbots and assistants.
  • Compare RAG and MCP with other architectures, evaluating trade-offs in performance, scalability, and deployment.
  • Hands-on assignment: Build a simple RAG or MCP-enhanced application using either an open-source framework or by integrating an API-based knowledge retrieval system.
• Module 5: Good Practices and Ethics
  • Address ethical considerations in AI, including data privacy, fairness, and bias detection/mitigation.
  • Learn responsible AI practices to ensure ethical and reliable model deployment.

Course schedule

Live sessions are mandatory; however, if you require an exception, please speak with the facilitator

• Week 1 | Participant Onboarding
  • No live sessions
• Week 2 | Module 1: Introduction and Fundamentals
  • January 13 & 15, 2026 (9:00AM - 12:00PM)
• Week 3 | Module 2: Building and Fine-Tuning LLMs
  • January 20 & 22, 2026 (9:00AM - 12:00PM)
• Week 4 | Break
  • No live sessions
• Week 5 | Module 3: Leveraging LLMs Through APIs and Integration
  • February 3 & 5, 2026 (9:00AM - 12:00PM)
• Week 6 | Module 4: Utilization of RAG and MCP
  • February 10 & 12, 2026 (9:00AM - 12:00PM)
• Week 7 | Module 5: Good Practices and Ethics
  • February 17 & 19, 2026 (9:00AM - 12:00PM)
• Week 8-9 | Capstone Project
  • February 24, 2026 (9:00AM - 12:00PM)
• Weeks 10-11 | Grading & Project Feedback

Course requirements

This program leverages open-source tools and libraries, such as Python, Hugging Face, PyTorch, and TensorFlow, to provide accessible and practical learning experiences. No paid subscriptions are required.

• Other software and hardware required:
  • Google account
  • Internet access
  • Laptop or desktop device (macOS or Windows)