AI Deployment & Operations
Cloud Deployment for AI Applications
O01 · Practitioner
Entry requirements
F01; G01 or M01; basic terminal skills
What 36 hours means
- Lessons
- 24 h
- Capstone
- 8 h
- Assessment
- 2 h
- Remediation
- 2 h
Syllabus
Four modules, twelve lessons. Every lesson states what it covers and the evidence you produce for it.
Module 1
Application packaging
Service boundaries · API implementation · Containers
O01Show lessonsHide lessons
O01.01 · 120 min
Service boundaries
Define API, storage and inference responsibilities.
Evidence: A component diagram records interfaces and failure points.
O01.02 · 120 min
API implementation
Build typed request validation and consistent errors.
Evidence: Invalid inputs do not reach inference execution.
O01.03 · 120 min
Containers
Create a reproducible image with a non-root runtime user.
Module 2
Cloud components
Configuration and secrets · Cloud building blocks · Infrastructure definitions
O01Show lessonsHide lessons
O01.04 · 120 min
Configuration and secrets
Separate public settings from short-lived credentials.
Evidence:
Module 3
Deployment
Delivery pipeline · Health and scaling · Monitoring
O01Show lessonsHide lessons
O01.07 · 120 min
Delivery pipeline
Build, test and publish a tagged image after checks.
Evidence:
Module 4
Operation
Cost controls · Rollback and recovery · Operations handover
O01Show lessonsHide lessons
O01.10 · 120 min
Cost controls
Apply quotas, expiry and teardown to training infrastructure.
Evidence:
Capstone
Containerise and deploy an AI service to a controlled environment with secret handling, health checks, monitoring and a tested rollback.
Lab environment
Developer sandbox; restricted cloud tenant optional
Lab infrastructure is not yet provisioned, so this describes the environment the course is designed for rather than one you can launch today.