Contact us
Contact us
*Changes may apply

GenAI Syllabus

Module 1: Fundamentals of Generative AI

 

  • Introduction to GenAI: History, evolution, and core concepts (Generative vs. Discriminative AI). 
  • Market Landscape: Overview of leading tools and platforms. 
  • LLM Architecture: Deep dive into the Transformer architecture, tokenization, and embeddings. 
  • Model Types: Understanding the differences between open-weight and closed-weight models. 
Module 2: Prompt/Context Engineering & Text Applications

 

  • Working with LLMs APIs: including Google Gemini, OpenAI, Anthropic as well as open-source models from HuggingFace. 
  • Prompt/Context Engineering Principles: From zero-shot and few-shot to advanced prompting techniques like chain of thought (CoT) and context handling. 
  • Understanding the Parameters: all the settings you can tweak to get the most of your llm, such as temperature. 
  • Development AI Frameworks: Introduction to LangChain and LlamaIndex. 
  • Evaluation driven development: how to evaluate GenAI products and what is the correct process? 
Module 3: Fine-tuning

 

  • Fine-tuning: What does it mean? 
  • Parameter efficient fine tuning: including LoRA. 
  • Understanding fine tuning of reasoning models: for example, DeepSeek-1. We will cover the underlying theory and conceptual foundations, without engaging in large-scale fine-tuning in practice.

 

Module 4: Retrieval Augmented Generation (RAG)
  • RAG Fundamentals: The need for external memory, vector databases, and semantic search. 
  • Basic Pipelines: Building a standard RAG system. 
  • Advanced RAG: Re-ranking, hybrid Search, and handling complex documents. 
  • Evaluation of RAG systems: Metrics and methods for evaluating RAG performance. 
Module 5: AI Systems
  • Workflows & Systems: what is an AI system and why RAG is just a specific case of it? Reviewing common architectures. 
  • Automation tools: such as n8n. 
  • How to build a workflow: best practices and tips. 
Module 6: AI Agents
  • Tool Use: Function calling and connecting LLMs to external APIs. 
  • MCP & Other protocols (such as A2A): Tool use 2.0
  • AI Agents: Differences between chatbots and agents (e.g., ReAct design pattern).