What AI engineering actually is
AI engineering is the discipline of building reliable products on top of frontier models.
It is not model training. You will almost never train a model from scratch, and in 2026 you will rarely fine-tune one either. It is also not prompt tinkering. Writing a clever prompt is to AI engineering what writing a clever SQL query is to backend engineering: useful, but nowhere near the whole job.
The job is everything in between: grounding models in your data, giving them tools, orchestrating multi-step agents, measuring whether the system actually works, and shipping something that holds up when real users touch it. Models are non-deterministic. The engineering is in building dependable systems out of undependable parts.
One more shift that defines the role right now: coding agents write most of the code. Tools like Claude Code and Cursor handle implementation, which means the scarce skill is no longer typing Python quickly. It is systems thinking, context engineering, and the judgment to evaluate what the agent built. That is what this page, and the bootcamp, are organised around.
What you need before Session 1
AI engineering is still engineering. Before the AI-specific pillars mean anything, you need the same baseline every backend engineer has. We do not spend live session time on these - we assume working familiarity and point you to gap-closers in pre-course.
Python
The working language of the field. You should read and debug it comfortably, even when a coding agent writes most of it.
Official Python tutorial →Git and GitHub
Version control is non-negotiable, and doubly so when an agent commits code you need to review. Branch, commit, diff, revert, open a pull request.
Introduction to GitHub (GitHub Learn) →APIs and HTTP
Requests, responses, status codes, auth headers, JSON. Every LLM call is an API call.
FastAPI docs →Docker
Containers are how AI systems ship. You should be able to read a Dockerfile, build an image, and run a container.
Docker getting started →Testing
The habit of proving code works. Evals are tests for non-deterministic systems, so the instinct transfers directly.
pytest documentation →Databases and SQL
Where your app's data lives, and increasingly where your vectors live too.
SQLBolt →The bar is working familiarity, not mastery. If you have shipped any software professionally, you likely clear it already. If two or more of these are new to you, spend time on the gap-closers first, or start with the Builder's Bootcamp instead.
What happens live
Five live sessions, then a two-week build sprint to Demo Day. Each session is a working session, not a lecture: we build, break, and reason about real systems together, and every session ends with something running on your capstone - the project you choose.
- →
Session 1 - FoundationsTurn a model call into a reliable component: context engineering, structured outputs, guardrails, and cost visibility.
- →
- →
- →
- →
What happens async
The async work is where the pillars become yours. One capstone runs through the whole course, and each session's assignment adds a layer: retrieval, agency, evals, memory. By Demo Day you have a deployed, evaluated agentic system - not a folder of exercises.
- Pre-course: coding-agent setup, Python, GitHub, capstone seed, building in public.
- Token optimisation and production-minded deep dives (Session 1 async modules).
- Mastering AI Engineering: curated continuation path after the course.
Budget 6 to 8 hours a week including the live session.
