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.
What is it?
What it is
A free 24-week AI engineering training program that takes beginners from Python to production-grade AI systems, covering machine learning, deep learning, LLMs, prompt engineering, RAG, fine-tuning, agents, cloud platforms, and Databricks.
Why it exists
Developed by Zorost Intelligence AI Lab to provide a hands-on, opinionated curriculum for engineers joining generative AI, applied machine learning, or Databricks modernization teams, bridging the gap between learning resources and production skills.
Who should use it
software developers adding AI, analysts moving toward engineering, students and career changers, technical founders
Who should avoid it
a research career in model architecture, or a weekend prompt workshop
How it works
A quick walkthrough in plain English
How AI-Engineering-Lab works
Step 1 of 3
You interact with it
Open AI-Engineering-Lab, send a request, or connect it to your stack.
Features
Advantages
- Completely free with permissive MIT license
- No prerequisites required (assumes basic computer literacy only)
- No paid API keys needed for most of the curriculum
- Self-paced with flexible 10 hours per week commitment
- Hands-on learning through executable notebooks rather than passive reading
- Real-world case study provides interconnected portfolio artifacts
- Teaches evaluation discipline and honest error documentation
- Covers end-to-end stack from fundamentals to production deployment
- Multi-cloud exposure builds platform-agnostic skills
- Structured guidance reduces decision fatigue for beginners
- Includes troubleshooting documentation and support pathways
- Graduates with tangible artifacts for professional portfolio
Disadvantages
- Requires significant time commitment (10+ hours weekly for 24 weeks)
- Self-directed learners without live instructor support or code reviews
- No peer collaboration or community learning component built in
- Jupyter Notebook format may not suit all learning styles
- May become outdated given rapid AI field evolution
- Freight logistics domain context may feel niche if not interested in that industry
- Dense curriculum could overwhelm absolute beginners despite 'no prerequisites' claim
- Quality of learning depends heavily on individual motivation and discipline
- Limited coverage of cutting-edge research or emerging architectures
- Cloud free tier limits may require careful cost management in later weeks
Installation
cloud
Free cloud notebook options available; Weeks 18-24 use cloud free tiers with guidance to stay within limits
native
git clone https://github.com/zorost/AI-Engineering-Lab.git && cd AI-Engineering-Lab && python -m pip install -r requirements.txt
FAQ
Do I need a GPU, a paid API key, or prior Python experience to start?
No. The program is designed for a motivated beginner with basic computer literacy. Weeks 1 to 8 require no GPU and no paid API keys, and the curriculum teaches Python from the ground up. A GPU becomes optional starting in Week 8, and Weeks 18 to 24 are built around free cloud tiers with guidance on staying within them.
How much time per week should I expect to commit?
About ten hours per week. Each week follows four beats: Study (Mon-Tue), Build (Wed-Thu), Ship (Friday), and Reflect (Fri-Sun). The Friday 'Ship' step requires one artifact, one metric, and one honest error-analysis note from Week 3 onward.
What is the ZoroLogistics case study and why does it matter?
It is a continuous fictional freight case study used across all 24 weeks. Week 1's seeded dataset evolves into Week 2's SQL practice, Week 3's training data, Week 7's retrieval corpus, Week 10's fine-tuning set, Week 16's agent tools, and Week 23's feature tables. You graduate with a portfolio of interconnected artifacts rather than 24 disconnected demos.
How do I get started after cloning the repository?
Run 'python -m pip install -r requirements.txt' from the repository root, then open the Week 1 folder at 'curriculum/week-01'. Week 1 sets up your machine and generates the dataset every later week reuses. Newcomers to programming or AI should read START-HERE.md first for the tool order and troubleshooting steps.
Where can I find the tracker and how do I use it?
The tracker lives in 'curriculum/tracking'. It is an Excel file that maps out each week's Monday row. After completing a week's Reflect step (a ten-question quiz you must pass at eight), you tick the corresponding tracker row to mark progress.
Is this program affiliated with or endorsed by DeepLearning.AI or Andrew Ng?
No. The curriculum implements Andrew Ng's AI Engineering Skills Map and his three loops for building software in the AI era, but AI Engineering Lab is an independent implementation. It is not affiliated with or endorsed by Andrew Ng or DeepLearning.AI. The Lab's own reading of the map is available at zorost.com/ai-engineering-skills-map-training-guide.
Featured in Videos
YouTube tutorials and walkthroughs for AI-Engineering-Lab
Alternatives
Similar projects ranked by category, topics, and text overlap.
