AI-Engineering-Lab
A free, self-paced 24-week AI engineering course: Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure and Vertex and Bedrock, and Databricks
What is AI-Engineering-Lab?
A free, self-paced 24-week AI engineering course: Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure and Vertex and Bedrock, and Databricks. 43 runnable notebooks, one continuous case study. MIT licensed, no signup. By Zorost Intelligence AI Lab.
Overview of AI-Engineering-Lab
What it is
AI Engineering Lab is a free, self-paced 24-week AI engineering course developed by Zorost Intelligence AI Lab. It covers Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure AI Foundry, Google Vertex AI, AWS Bedrock, and Databricks. The program includes 43 runnable notebooks and one continuous case study. It is MIT licensed and requires no signup.
Key features
- 24-week curriculum with weekly beats: study, build, ship, reflect.
- One continuous fictional freight case study (ZoroLogistics) used throughout all weeks.
- Covers foundations (Python, ML, deep learning), LLM core, model engineering, harnesses and loops, agents, cloud AI platforms, and Databricks.
- From Week 3 onward, every AI artifact ships with a metric and an error-analysis note.
- No GPU needed for the first eight weeks; free path using local models, free-tier APIs, or no API for weeks 1–13.
- Repository includes curriculum folders, reference knowledge base, agent patterns, platform guides, and a glossary.
Use cases
- Software developers adding AI to their skillset.
- Analysts moving toward engineering roles.
- Students and career changers seeking a structured, hands-on AI engineering roadmap.
- Technical founders needing a production-oriented AI curriculum.
Getting started
bashgit clone https://github.com/zorost/AI-Engineering-Lab.gitcd AI-Engineering-Labpython -m pip install -r requirements.txtRead START-HERE.md first. Open curriculum/week-01 to set up your machine and generate the dataset. Open the tracker in curriculum/tracking and follow the Monday row.
License and pricing
MIT licensed. Free, no signup. Weeks 1–13 have a free path using local models, free-tier APIs, or no API. Weeks 18–24 use cloud free tiers. A GPU is optional until Week 8.
Based on the project's public README and repository metadata.