Full stack AI development
Go from building screens to shipping AI features that run in production, in 26 weeks.
AI engineer is the fastest-growing job on LinkedIn’s 2026 listLinkedIn Jobs on the Rise 2026
- 26 + 4
- core + track weeks
- ~40 h
- a week
- 5
- milestone projects
- 158
- subtopics, 31 topics
What you will be able to do
- 01
Build a production backend: Django and FastAPI, SQL, login, background jobs, payments and tests.
- 02
Add AI to a product: LLM APIs, structured output, tool calling, RAG, agents and chat interfaces.
- 03
Measure and protect it: evals, cost and speed, tracing, and security for AI features.
- 04
Deploy it on AWS with Docker, Terraform and CI/CD, then watch it in production.
- 05
Finish with a capstone you can show, interview preparation and a live job search.
01The route
Six months, one month at a time.
Each month ends in a milestone project, so you always have something to show for the work.
Month 1 · Weeks 1–4
Backend foundations
Python, SQL and PostgreSQL, Django and REST APIs, login, permissions and tests.
MilestoneA multi-tenant API with tests running on GitHub
Month 2 · Weeks 5–8
Production backend
Background jobs, caching, files, payments, async Python and FastAPI, Docker, real-time chat.
MilestoneA real-time app with logs and metrics
Month 3 · Weeks 9–13
AI engineering, the core
How LLMs work, structured output, tool calling, embeddings, RAG and its quality, AI interfaces.
MilestoneAn AI product with a streaming chat interface
Month 4 · Weeks 14–17 + tracks
AI engineering, advanced
Evals, agents, AI security and reliability, cost, speed and tracing. Tracks: MCP, workflows, fine-tuning.
MilestoneAn agent you can measure, trace and defend
Month 5 · Weeks 18–22 + track
Cloud, DevOps and security
AWS, containers, Terraform and CI/CD, observability and reliability, security.
MilestoneThe product deployed on AWS with infrastructure as code
Month 6 · Weeks 23–26
Capstone and job search
Polish the product and tell its story, interview preparation, a speed project, applications and offers.
MilestoneA capstone and a working job-search pipeline
02The tools
See the whole route, not only this week.
Three views come with the roadmap. Here is a glimpse of each; the rest opens when you own it.
Swim lanes
All 26 weeks on one chart: what you study, which checks run through it and when you ship.
Skill map
Every topic and how they connect, so you can see what you already know and what unlocks next.
Milestone tracker
Five projects to build and tick off. Step through them and the architecture grows with each one.
03What is inside
Everything a week comes with.
Every week is built the same way, so once you have done one you know how all of them work.
- 01
A day-by-day plan
Every week is split into study days with what to learn, what to do and how to check yourself.
- 02
A project in every milestone
Five milestones, each ending in something you can put on your CV and link to.
- 03
"Done when" checklists
Every week ends with a checklist, so you know you are finished instead of guessing.
- 04
Read it three ways
By week, by topic, or as a flow chart and swim-lane picture of the whole route.
- 05
Progress in your Study plan
Add weeks to your study plan, give them dates, and finished days are counted for you.
- 06
Handbooks to go deeper
Linked handbooks on the topics in the roadmap, when a week needs more than a summary.
04Is it for you
Who this is, and is not, for.
Better to know before you start than six weeks in.
It is for you if
- You can already build a frontend and want to own the whole stack.
- You want AI engineering skills that employers ask for, in a fixed order.
- You can give about 40 hours a week for six months.
It is not for you if
- You have never written code. Start with a beginner course first.
- You want a job guarantee. Nobody can promise that, and this roadmap does not.
?Questions
Before you start
- Can I see some of it before buying?
- Yes. This page shows the real month-by-month route, the three planning views (just a glimpse — they unlock in full once you own it) and every outcome it teaches, so you can judge the format before you commit.
- How long does it take?
- About 40 hours a week for 26 weeks, plus four optional track weeks. If you have fewer hours, add weeks to your study plan at a slower pace.
- What if I fall behind?
- The plan moves with you. Days you miss stay in your study plan and can be rescheduled; nothing expires.
- Will it get me a job?
- It gives you skills and proof of work. It cannot promise a job on a fixed date, because hiring depends on the market, your location and your past work.
Ready to start?
Buy once to open every week, or see all roadmaps.