Contact us
Contact us
*Changes may apply

GenAI Syllabus

Segment 1: Large Language Models

 

  • Fundamentals: 
    • Key Concepts: Fundamental principles and terminology. 
    • Developing Language Models: Evolution from GPT-3 to ChatGPT, including Instruction Tuning and Reinforcement Learning with Human Feedback (RLHF).
  • Knowing the landscape: 
    • Industry Landscape: Analysing the main players in the field, including both open-source and proprietary models.
  • Prompt Engineering: 
    • What is it and how to do it well 
    • Few-shot (AKA in context learning) vs. Instruction 
    • Common techniques
  • Customization Techniques: 
    • Fine-tuning 
    • Parameter-efficient tuning (PEFT) 
    • When to use fine tuning? 
    • The rise of SLMs
  • Evaluation: 
    • Why is it SO hard? 
    • Known benchmarks & leaderboards review 
    • Classical methods 
    • Using LLM as a judge, reward & critique models.
  • Reasoning: 
    • From CoT to Large Reasoning Models, o1, o3, Claude extended thinking. 
Segment 2: AI Systems / Workflows

 

  • Retrieval Augmented Generation (RAG): 
    • Overview: what is RAG. 
    • Indexing & Chunking. 
    • Retrieval: embeddings + semantic search and other methods 
    • Best practices and considerations vs. long context. 
    • Llama Index overview
  • Static chains: 
    • Breaking complex tasks into chains 
    • LangChain overview
  • Function calling / tool use: 
    • What is it and how to use it
  • Pre & Post Processing: 
    • Cleaning, chunking
  • Workflows & Systems: 
    • Common methods for pre-processing of data 
    • Filters and methods to handle outputs, especially hallucinations 
    • Generate and fix vs. Best-of-N – what is better?
  • LLM as a router + SLMs. 
Segment 3: AI Agents

 

  • AI Agents overview: 
    • What is an Agent? 
    • Agents vs. Workflows 
    • The agents landscape 
    • Introduction to LangGraph
  • Building AI Agents: 
    • Frameworks overview (Google Vertex, AutoGen, CrewAI)