This course starts with the fundamentals of Generative AI, including autoencoders, VAEs, GANs, and the evolution of Large Language Models. You will gain practical expertise in prompt engineering, system setup, and adversarial prompt defense. The course dives deep into vector databases, embeddings, LangChain, and the open-source Gen-AI ecosystem.

Learners will design and implement Retrieval-Augmented Generation (RAG) systems, covering data ingestion, storage, retrieval, evaluation, observability, and guardrails. Advanced topics include LLM fine-tuning, hybrid retrieval, reranking, query expansion, and advanced RAG techniques such as Agentic, Multimodal, and Fusion RAG.

The course concludes with building and deploying production-grade Gen-AI applications using Streamlit, Docker, AWS, and CI/CD pipelines, along with two end-to-end capstone projects to demonstrate real-world readiness.