Skip to content
AIETechnical

AI Engineering

Engineers building LLM applications, retrieval systems and agents who need them to hold up in production.

Length

8 weeks, part-time

Commitment

~7 hours per week

Cohort

12 live sessions, 20 seats

Before you start

What this track assumes

Professional software engineering experience. Python or TypeScript.

What you cover

7 modules

Each one is worked through live, then built on between sessions.

  1. 01Architecture of an LLM application — boundaries, state, failure behaviour
  2. 02Retrieval that works — chunking, hybrid search, reranking, grounding and citation
  3. 03Evaluation harnesses — golden sets, rubrics, LLM-as-judge and its failure modes
  4. 04Testing non-deterministic systems and running evals in CI
  5. 05Agents with bounded authority — permissioning, idempotency, blast radius, injection
  6. 06Inference economics — routing, cascades, caching, context budgets, unit cost
  7. 07Operating it — tracing, drift, incident response and model migration
How you are assessed

You build it, then you defend it.

There is no exam and no pass for attendance. Some people do not pass first time.

The project

A working evaluation harness over a real system of your own, with a documented change that the harness shows to be an improvement.

Take AI Engineering.

6 weeks, 12 live sessions, 20 seats, priced by region from $450. Places in the first cohorts are arranged directly.