Intermediate · 2 days
AI Systems on AWS
A two-day course for cloud engineers, developers and architects: design and build AI systems on AWS, with architecture first and managed services in their proper place.
2 days · Intermediate · Cloud & Platform · Cloud engineers, developers and architects
Overview
AWS offers a dense set of managed AI services. Teams that start from the product list often produce designs that are hard to move, hard to evaluate and expensive to run. This course starts from the system: model access, identity, retrieval, orchestration, events, security and cost. AWS services are then used as implementations of those parts.
You cover managed foundation models, identity and IAM, storage, serverless patterns, RAG and vector search, agents, event-driven systems, observability, deployment, security and cost. Service names are taught as current implementations, not as the architecture itself, so the design still holds when the console labels change.
The course is practical. You design and build against AWS primitives for model access, retrieval and an application path, then review the security and cost of what you built.
You leave able to design an AI system that happens to run on AWS, rather than an AWS diagram that happens to mention a model.
Audience
Cloud engineers, developers and architects working on AWS who will design or implement AI systems.
Prerequisites
Working knowledge of AWS identity, networking and at least one compute option (functions, containers or virtual machines). Familiarity with LLM applications is helpful.
Duration
2 days
Can be aligned to your organisation’s AWS estate, landing zone and approved services.
Learning outcomes
- 01
Design an AI application architecture on AWS with explicit identity, data and model boundaries.
- 02
Integrate managed foundation models through a controlled access path rather than scattered credentials.
- 03
Implement RAG using storage, search and retrieval services appropriate to the corpus and tenancy model.
- 04
Place agents and event-driven workloads on queues and workflows with IAM-scoped tools.
- 05
Apply observability, security and cost controls that are native to the platform.
- 06
Deploy a working path and know which parts are portable if the model provider changes.
Outline
- 01
Architecture, then services
- A portable AI architecture: gateway, orchestration, retrieval, tools, evaluation.
- Model access on AWS: managed foundation models, and when self-hosted inference is justified.
- IAM, secrets and the failure mode of long-lived keys in application code.
- Lab: a controlled model-access path with least privilege.
- 02
Data, RAG and application paths
- Storage, document ingestion and vector search options.
- RAG on AWS without collapsing search, generation and permissions into one service.
- Serverless and container patterns for synchronous assistants.
- Lab: ingest, retrieve and generate with citations.
- 03
Agents, events and operations
- Agents and tool calling with IAM-scoped actions.
- Event-driven generation, queues, retries and human review.
- Observability, security, networking and cost.
- Deployment and a review of lock-in versus speed.
- Lab: an event-driven or tool-using path with tracing and a cost estimate.
Practical work
You build a small AWS-backed AI path: authenticated model access, a retrieval component, and either a synchronous application or an event-driven job. The closing review covers IAM, cost, observability and which interfaces should stay portable.
Takeaways
- A working AWS implementation of a small AI system
- Reference architectures mapped to current AWS services
- IAM, cost and observability checklists
- A portability note: which interfaces to keep stable
Delivery
Cognitecta delivers private corporate training, on-site or as remote live training. Courses can be run as published, or adapted to your organisation’s stack, domain and experience level.
Instructor
Nicholas Johnson, AI architect and software engineer. He has a degree in Artificial Intelligence and around twenty years of professional technology training, including hundreds of courses for engineering teams and large organisations. About.
Related courses
2 days · Intermediate
AI Systems on Azure
A two-day course for cloud engineers, developers and architects: design enterprise AI systems on Azure, including identity, search, model APIs and the architecture those services should sit inside.
2 days · Advanced
AI Platform Engineering
A two-day course for platform engineers, architects and senior developers: build the internal infrastructure that lets multiple product teams use AI safely and consistently.