Module 1: Python & Machine-Learning Foundations
Build the programming, data-handling, probability, and model-evaluation foundations needed for later generative AI work.
Course Specialization
EnrollGenerative AI & LLM Engineering
Program Overview
Progress from Python and machine-learning foundations to transformer concepts, retrieval systems, evaluation, integration, and responsible deployment.
Skills & Tools
- Python
- Machine Learning Foundations
- Transformers & LLMs
- Embeddings & Vector Search
- RAG
- Evaluation
- Model APIs
Course Curriculum
Module 2: Transformers & LLM Concepts
Understand tokens, embeddings, attention, context, training stages, inference, limitations, and common model families at a practical level.
Module 3: Prompt & Context Engineering
Structure instructions, examples, context, output formats, and safety boundaries, then test prompts systematically.
Module 4: Embeddings & Vector Search
Prepare content, create embeddings, compare retrieval strategies, use vector stores, and evaluate search quality.
Module 5: Retrieval-Augmented Generation
Build RAG pipelines with source attribution, access-aware retrieval, grounding checks, and clear failure behavior.
Module 6: Evaluation & Responsible AI
Define test sets and quality criteria, inspect bias and failure modes, protect sensitive data, and design meaningful human oversight.
Module 7: Model & API Integration
Connect model providers and supported open models through resilient APIs, structured outputs, tool calls, caching, and cost controls.
Module 8: Deployment Capstone
Deliver a documented generative AI application with evaluation evidence, monitoring signals, access controls, and an operational handoff.
Capstone Projects
Grounded Knowledge Assistant
Build and evaluate a retrieval-based assistant that cites approved sources and communicates uncertainty clearly.
Generative AI Deployment Capstone
Ship a scoped generative AI workflow with testing, observability, responsible-use controls, and documented limitations.