Deploying GenAI with RAG on AWS

This unit consolidates GenAI concepts into practical, cloud-based solutions by focusing on Retrieval-Augmented Generation (RAG) design, implementation on AWS, and hands‑on labs and notebooks. It also addresses real-world case studies, operational challenges, ethical implications, and strategies to stay current with rapidly evolving generative AI technologies.

Learning Objectives

• Analyze RAG architectures, components, and trade-offs using case studies to select appropriate retrieval, indexing, and generation strategies for given problems
• Apply AWS GenAI services (e.g., Amazon Bedrock, Amazon Q) and custom data pipelines to build, deploy, and test a functioning RAG solution and NL query engine
• Demonstrate the ability to construct, troubleshoot, and document agentic LLM assistants and RAG workflows using provided example notebooks and labs
• Evaluate technical, ethical, and operational risks (including bias, hallucination, privacy, and scalability) and propose mitigation and continuous‑learning strategies to maintain safe, effective GenAI systems