AI curriculum
Course outline for AI Infrastructure
Model deployment choices affect latency, cost, and data handling. Design serving and routing infrastructure around a defined workload and compare local and managed options.
About AI Infrastructure
Model deployment choices affect latency, cost, and data handling. Design serving and routing infrastructure around a defined workload and compare local and managed options.
AI Infrastructure Course Objectives
- Describe serving resource and GPU requirements.
- Define gateway and model routing policies.
- Compare local inference with managed model platforms.
Pre-requisites
- Familiarity with cloud deployment and APIs.
- Basic understanding of model inference.
Lab Setup
- Computer with a programming runtime and local mock model endpoints.
- GPU hardware and managed model accounts are optional; use supplied capacity traces when unavailable.
- Keep service access nonproduction and avoid confidential prompts.
Detailed Course Outline
Proposed modulesModule 1: Serving architecture
- Model serving
- GPUs
- Inference infrastructure
- AI gateways
Practical outcome: Specify serving capacity assumptions and gateway controls.
Module 2: Routing and deployment choices
- Model routing
- Local vs cloud inference
- AWS Bedrock
- Managed model platforms
Practical outcome: Compare deployment paths against workload constraints.
Practical exercise
- Design an inference gateway and test routing behavior with local or mocked model endpoints.
How we train
Contact us for full course details, including duration, delivery options and lab requirements.
Ask about exercises, instructor feedback and the prior knowledge you need. Tool-specific courses marked provisional may become modules in a broader course.
Discuss your learning goals