Generative AI & LLM Application Engineering
Large language models have become the core building block of modern AI products. This module builds real LLM-powered applications — from prompt engineering through to full Retrieval-Augmented Generation systems.
What You Will Learn
A detailed, industry-aligned breakdown of every topic covered in this module.
- Generative AI fundamentals
- Large language models
- LLM APIs and prompt engineering
- Structured outputs and function calling
- Embeddings and vector databases
- Document ingestion and chunking
- Retrieval-Augmented Generation (RAG)
- Reranking and RAG evaluation
- PostgreSQL and pgvector
- Model Context Protocol (MCP) fundamentals
Tools You Will Use
Hands-on time with the same tools used in professional AI engineering and production ML workflows.
LLM APIs
Large language model APIs used to integrate generative AI capabilities into applications.
Hugging Face
Model hub and library ecosystem used to access, fine-tune and deploy AI models.
LangChain
Application framework used to build LLM-powered applications with chains and tool integrations.
PostgreSQL
Relational database used to store structured application and AI system data.
pgvector
PostgreSQL extension used to store and query vector embeddings for semantic search.
Vector DBs
Purpose-built databases used to store and retrieve embeddings for RAG and semantic search.
FastAPI
Modern Python web framework used to build production-grade backend and AI-serving APIs.
Docker
Containerization platform used to package and deploy applications and AI services consistently.
MCP
Model Context Protocol used to connect AI agents and LLMs to external tools and data sources.
Hands-On Labs
Production-style AI engineering lab scenarios, built using the same stack real AI teams ship with.
Engineer prompts and use structured outputs and function calling with an LLM API.
Build a document ingestion and chunking pipeline for retrieval.
Generate and store embeddings in a vector database using pgvector.
Build a full Retrieval-Augmented Generation (RAG) application end to end.
Evaluate and improve RAG quality using reranking and evaluation techniques.
Assessment
Knowledge Assessment
Quiz covering LLM fundamentals, embeddings, vector search and RAG architecture.
Practical Evaluation
Students must build and demo a working RAG application that answers questions from a real document set.
Projects
Industry-style deliverables added directly to your project portfolio.
Generative AI / RAG Application
Build LLM-powered apps with RAG, vector search and document understanding.
What This Module Builds
Students learn to build LLM-powered applications, integrate AI models with external data and APIs, develop RAG systems, implement vector search and ship practical Generative AI applications.