MLOPS & CLOUD / CORE

MLO401Software delivery for AI: APIs, tests, Docker & CI

32 h productive allocation12 h 48 m learning + 19 h 12 m training4 units · 1 assessed practical brief

Detailed course plan and training brief. A complete taught course pack is in preparation. The linked foundation module, where shown, is a smaller available resource.

BEFORE YOU BEGIN

A clear starting point.

Prerequisites: AI101 · ML201

Core studio / CPU-friendly local or notebook environment

WHAT YOU SHOULD BE ABLE TO DEMONSTRATE

Explain the assumptions and failure modes in inference as an api.
Complete the practical: package a baseline model behind a validated local API, test it, containerise it and prepare a CI workflow for a clean build.
Defend the resulting api contract with reproducible evidence.

THE SUBJECTS / FOUR CONNECTED UNITS

What you will study.

UNIT 018 h allocated

Inference as an API

HTTP and JSON
FastAPI
input validation
batch versus online contracts

UNIT 028 h allocated

Tests that protect behaviour

Unit and integration tests
data-contract checks
deterministic fixtures
failure responses

UNIT 038 h allocated

Container engineering

Images and containers
Dockerfile
volumes and networking
non-root processes

UNIT 048 h allocated

Continuous integration

Pull-request checks
build artefacts
dependency scanning
release and rollback

THE TRAINING STUDIO

Make the subject
visible in your work.

Package a baseline model behind a validated local API, test it, containerise it and prepare a CI workflow for a clean build.

Evidence to produce

API contract
test report
Dockerfile and image recipe
CI configuration

Training brief for supervised delivery. Code, datasets, answer keys and environment acceptance must be completed in the full course pack before delivery is confirmed.

ASSESS THE REASONING

A question you
should be able to answer.

What must a clean machine have to reproduce your service without your notebook session?

Review dimensions

Technical correctness · reproducibility · interpretation of results · failure analysis · individual explanation. Course-level rubric and faculty moderation form part of the final adopted teaching pack.

Continue in the official reference ↗Programme assessment framework →

External reference access, hardware, cloud accounts and paid services are separate. No third-party certification is included by implication.