AI Engineering: Building Production LLM Applications

Descrizione del corso

The AI Engineer's complete playbook for production systems. Covers LLM application architecture patterns (gateway, routing, fallbacks), latency optimization techniques (streaming, batching, caching with GPTCache/Redis), prompt injection defense, output parsing and structured generation (Instructor, Outlines), rate limiting and cost management, multi-model routing (LiteLLM), load testing LLM endpoints, blue/green prompt deployments, and building internal developer tooling for AI teams.

Cosa imparerai

• Curated from public resources. End-to-end guide to shipping LLM applications to production: architecture, latency optimization, caching, safety, and observability.

Programma del corso

1. LLM gateway pattern: routing, fallbacks, retries (35 min)
2. Multi-model routing with LiteLLM (30 min)
3. Streaming responses: SSE, WebSocket, and chunked transfer (28 min)
4. Prompt caching strategies: semantic and exact match (32 min)
5. Batching requests for throughput vs latency trade-offs (25 min)
6. Prompt injection: attacks, defenses, and detection (40 min)
7. Structured output generation with Instructor and Outlines (35 min)
8. Hallucination detection and grounding techniques (38 min)
9. Blue/green prompt deployments and canary releases (30 min)
10. Load testing LLM endpoints with Locust (28 min)
11. Building internal AI developer portals (25 min)

Struttura del corso

4 sezioni, 11 lezioni, 15h 0m di durata complessiva. Il corso si segue interamente online, al proprio ritmo.

Domande frequenti