Free · no sign-in
Getting Started with AI
8 sessions · Beginner
Eight sessions on how language models really behave: tokens and sampling, cost and latency, prompts and context, structured output, choosing a provider, and using AI responsibly.
Flagship guided program · AI/ML Engineer track
Become the engineer who can take AI from idea to working feature.
A Forward-Deployed Engineer works close to the problem: understanding what a team needs, directing AI and coding tools at the work, and shipping a production feature that can survive contact with real users. This program is for people who already know software development and want to make that experience useful in AI-enabled delivery.
Apply / book a callThe order is deliberate
We do not start by asking you to memorise another stack. The program starts with AI/ML fluency and the practitioner skill of directing AI coding and agentic tools. Traditional application and delivery work comes next, as the layer where that fluency becomes useful.
You are not expected to be new to programming. You should be comfortable reading and changing software, working with a repository, and reasoning about a deployed service. You may come from backend, DevOps, QA, or another technical role; the program makes the common AI foundation explicit before the FDE tail becomes hands-on.
Start with the free courses
The foundation of this program is public. Read it online, free and without signing in, before you decide on anything.
Free · no sign-inBuilding AI Agents
11 sessions · Intermediate
Eleven sessions on agents that take real actions: tool calling, the Model Context Protocol, the agent loop, memory, access control, human approval and guardrails, ending in a capstone feature.
Free · no sign-inTaking AI to Production
9 sessions · Intermediate
Nine sessions on running AI systems for real: where models run, reference architectures, scaling, cost, observability and audit, ending in a design you defend with decision records.
Program shape
One spine, six stages
Plan for roughly 4–6 months part-time. The exact pace is shaped around your starting point and the depth of the capstone.
Stage 1
1. Build the AI fluency spine
Understand what models compute, how cost and latency shape a product, and how to direct AI coding tools with precise prompts, context, and machine-usable output.
- What a language model actually computes
- Context engineering
- Provider abstraction and model selection
Stage 2
2. Ground answers in real data
Move from impressive demos to systems that can retrieve, cite, and explain the data behind an answer, while recognising when retrieval is failing.
- Embeddings and vector search
- Retrieval-augmented generation end to end
- Fine-tuning, retrieval, or prompting
Stage 3
3. Build tool-using systems safely
Use tools, protocols, memory, and orchestration to make an AI system do useful work without treating autonomy as a substitute for engineering judgment.
- Tool use and function calling
- Model Context Protocol
- Multi-agent patterns
Stage 4
4. Make production behaviour observable
Evaluate outputs, detect hallucinations, apply guardrails, and instrument AI systems so a team can understand and improve them after release.
- Evaluation suites
- Hallucination detection and containment
- Security for AI systems
Stage 5
5. Ship inside an existing codebase
Apply the spine to unfamiliar repositories: direct AI coding tools at real work, integrate a feature, and reason through what changes when it misbehaves in production.
- Directing AI coding tools at real work
- Getting productive in an unfamiliar codebase
- Working forward-deployed
Stage 6
6. Produce evidence of the work
Finish a grounded, tool-using feature and turn the engineering decisions, trade-offs, and results into evidence you can discuss with a hiring team or client.
- Capstone: ship a grounded, tool-using feature
- Turning the build into evidence
What makes this FDE-shaped
Shipping over showcasing
A polished prompt demo is not the finish line. You will practise moving through an existing codebase, making a bounded change, validating it, and explaining what you chose not to automate.
Technical and human work
The role sits close to users and stakeholders. Scoping ambiguity, asking the right question, communicating trade-offs, and turning feedback into the next useful slice are part of the engineering work.
Evidence, not inflated promises
The capstone gives you a concrete system and a decision record to discuss. We do not publish invented placement numbers or pretend that one project guarantees a job.
Interview preparation in context
System design, debugging, behavioural discussion, and explaining an AI-assisted decision are woven into the work rather than sold as a separate add-on.
Proof is being built carefully
The AI-first framing is new. We will publish alumni stories only when the underlying outcome is verified and the person has consented to the use of their name or details.
Frequently asked questions
Do I need a computer-science degree?
No degree is assumed. Practical software experience is the important prerequisite: you should already be able to work in code and understand the basics of shipping a service.
Is this an introductory coding course?
No. It is designed for lateral-entry professionals who already work in or around software. The teaching starts with AI fluency, not syntax or a beginner programming sequence.
How long does it take?
The realistic public estimate is 4–6 months part-time. Your exact schedule depends on your starting point, available weekly time, and the scope of the capstone.
How is pricing decided?
Guidance-based pricing — talk to us. We discuss fit, background, and the delivery shape before quoting rather than placing a fixed shopping-cart price on a program that is meant to be adapted.