Fundamentals of AI Engineering: Principles and Practical Applications

About Course

Transform your software engineering skills into AI engineering capabilities with this in-depth, hands-on course. Learn how to build production-ready AI systems, from embedding generation to model deployment. Master practical implementations of vector stores, RAG systems, and hybrid search while gaining expertise in operational aspects like monitoring and CI/CD. Plus, learn to use GitHub Codespaces to build real-world applications that showcase modern AI engineering practices.

This course is integrated with GitHub Codespaces, an instant cloud developer environment that offers all the functionality of your favorite IDE without the need for any local machine setup. With GitHub Codespaces, you can get hands-on practice from any machine, at any time—all while using a tool that you’ll likely encounter in the workplace.

Course content

Introduction

What you should know

Course structure

What is AI engineering?

From deterministic to probabilistic systems

Running inference locally

Deconstructing the LLM

Putting the LLM pipeline together

Text extraction overview

Text extraction fundamentals

Document parsing and structure recognition

Metadata enrichment and indexing

Chunking strategies

Introduction to embeddings

The embedding ecosystem

Comparing embedding models

Efficient embedding generation

Challenge

Solution

Introduction to vector databases

Basic operations

Persistence and performance

Scaling strategies (approximate nearest neighbor, or ANN)

Scaling strategies (caching)

Introduction to retrieval engineering

Implementing BM25 and vector search

Building a hybrid retriever

Enhancing retrieval with reranking

Building a complete retrieval pipeline

Observability

Next steps and resources

Munich Ventures Academy

Erna Stepanyan

HATSR%5a52t35a4!