Retrieval-Augmented Generation (RAG) Systems

Who Should Attend

• Data Engineers: Engineers building ingestion pipelines for RAG systems.
• ML Engineers: Engineers tuning retrieval and generation quality.
• Backend Developers: Developers exposing RAG systems through application APIs.
• Solutions Architects: Architects designing knowledge-grounded AI systems.
• Data Scientists: Scientists evaluating retrieval and answer quality.

Prerequisites

This is an intermediate course. To get the most from it, you should have:

• ›

  Working knowledge of Python.

• ›

  Familiarity with vector or document databases is helpful.

• ›

  Basic exposure to LLM APIs.

Learning Objectives

In this course, you will learn to:

• ✓

  Design ingestion pipelines: Chunk, embed and index documents for retrieval.

• ✓

  Tune retrieval quality: Select and evaluate embedding and re-ranking strategies.

• ✓

  Ground generation: Combine retrieved context with LLM prompting reliably.

• ✓

  Evaluate accuracy: Measure and improve answer relevance and faithfulness.

• ✓

  Operate in production: Monitor freshness, cost and latency of a live RAG system.

Certification

This course does not map to a vendor certification exam. It builds the practical skills behind My Code Campus’s own forward-deployed RAG work with enterprise and healthcare clients. Every participant receives a My Code Campus certificate of completion.