The Gen AI course syllabus has 17 modules that run from Python and SQL through machine learning, deep learning and NLP to LLMs, RAG, AI agents, Databricks and a capstone project. The table below shows how the modules are grouped.
Module 1Foundation and career readiness
Professional discipline, career planning, LinkedIn profile
Module 2SQL and data modeling
Joins, window functions, schema design, data validation
Modules 3–4Python for Gen AI
Python fundamentals, OOP, NumPy, Pandas, file handling
Modules 5–7AI, machine learning and deep learning
ML algorithms, model evaluation, neural networks, transformers
Module 8Natural language processing
Tokenization, embeddings, NER, BERT and GPT basics
Module 9Generative AI core
LLM architecture, prompt engineering, vector embeddings, intro to RAG
Modules 10–11LangChain and advanced RAG
Chains, FAISS, vector search, re-ranking, RAG evaluation
Modules 12–14Agentic AI
ReAct agents, AutoGen, CrewAI, LangGraph, multi-agent systems
Module 15Enterprise AI with Databricks
Lakehouse, Delta Lake, Mosaic AI, MLflow, Unity Catalog
Module 16Capstone project
End-to-end Gen AI system
Module 17Career and placement preparation
Portfolio, resume, mock interviews
RAG, or retrieval-augmented generation, lets a language model answer from your own documents instead of relying only on what it was trained on. That is why two full modules and your capstone focus on it.