Full-stack AI product and portfolio

Build, evaluate and ship a complete AI product, from the interface to the release.

This is you

You want to build a whole AI product yourself, from the screen that users see to the release. You may want to start a company, or show a complete project to an employer.

Where you are going

A full-stack AI engineer

Design an AI product with clear requirements and costs
Build its interface, API, data and AI features
Secure it for many users and many organizations
Ship it, and show the evidence that it works

3 stages
20 courses, 20 available now
About 284–390 hours of study
19 certificates of completion

How much code you need

No code
Read code
Some code
Code is central

Code is central, and this is the longest path. The optional course on AI-assisted development comes early: with it, an assistant helps you write and review the code of every later course.

Your route, stage by stage

Each stop is a course. Its shape tells you how much of it to take.

Full course. The whole course, with its practice. It leads to a certificate of completion.
Concepts. Only the concept modules, read without running code. They lead to a concepts certificate.
Optional. Useful for some people. You do not need it, and it is not counted in the time.

You, today
Stage 1 Foundationsabout 51–69 h
1. AI Career Foundations: Roles, Skills and Roadmaps
  Full course4–6 h
  Plan your product and your portfolio.
2. Python for Practical AI Engineering
  Full course18–24 h
  Python for the AI parts of your product.
3. Git and Team Development Essentials
  Full course5–7 h
  Version control for a real product.
4. AI-Assisted Software Development
  Optional10–13 h
  Build faster with an AI assistant, and check its work.
  Focus: Recommended: no later course needs it, but it saves you time in every one.
5. Essential Mathematics and Statistics for AI
  Full course12–16 h
  The numbers behind quality and cost.
  Focus: If you already studied this, do its final assignment instead.
6. SQL and Data Preparation for AI
  Full course12–16 h
  The data that your product needs.
Stage 2 AI featuresabout 74–100 h
1. LLMs: How They Work and How to Choose One
  Full course8–12 h
  Choose the model for your product.
2. Building Reliable Applications with LLM APIs
  Full course22–30 h
  Build reliable LLM features.
3. RAG: Building AI That Uses Your Data
  Full course24–32 h
  Answers from your product’s own data.
4. Evaluating and Testing AI Systems
  Full course20–26 h
  Know that your AI features are good enough.
Stage 3 The whole productabout 159–221 h
1. Build and Deploy Your First API
  Full course11–15 h
  Your product’s API.
2. Docker and Cloud Essentials for AI Developers
  Full course7–10 h
  Containers and the cloud.
3. Databases and Storage for AI Applications
  Full course16–22 h
  Databases and storage.
4. Scaling APIs and AI Workloads
  Full course17–23 h
  Stay fast when users arrive.
5. Frontend Architecture and Performance for AI Apps
  Full course20–26 h
  The interface that users see.
6. Authentication, Permissions and Multi-Tenant Applications
  Full course16–22 h
  Sign-in, permissions and many organizations.
7. AI Security, Privacy and Responsible Design
  Full course18–24 h
  Security, privacy and responsible design.
8. CI/CD, Testing and Safe Releases
  Full course8–12 h
  Release safely, again and again.
9. AI System Design and Cost Engineering
  Full course16–22 h
  Design the system, and control its cost.
10. Portfolio Capstone: Build, Evaluate and Ship an AI Product
  Full course30–45 h
  The finish line: build, evaluate and ship your product.
You arriveA full-stack AI engineer

Earn certificates as you go

You do not need to finish the whole path to show what you learned. Each full course gives a certificate of completion, and each concepts course gives a concepts certificate. Share each one when you get it.

When you are ready, prepare for the interview: Interview preparation: Backend Engineer for AI products

Make it my path All learning paths

Choose this goal in your profile. My learning then shows your progress on this route, and the weeks it takes at your pace.