← All paths

Generative AI Engineer

Build reliable LLM apps, RAG systems and agents.

Advanced ~16 weeks·Engineers building on top of LLMs.

Recommended topic order

Weekly learning plan

Weeks 1–3

  • · Async & httpx
  • · Pydantic structured output

Weeks 4–7

  • · LLM SDK integration
  • · Tool calling & streaming

Weeks 8–11

  • · Embeddings & vector stores
  • · RAG pipelines & reranking

Weeks 12–16

  • · Agents & multi-agent workflows
  • · Eval, tracing & cost control

Required projects

  • RAG API
  • LLM gateway
  • AI-agent API
  • RAG evaluation dashboard

Interview topics

Async LLM callsRAG retrievalTool callingGuardrailsEval & tracing

Portfolio expectations

  • · A deployed RAG or agent service with eval, tracing and cost tracking

Job-readiness checklist

  • Calls LLMs async with retries and timeouts
  • Builds a RAG pipeline with citations
  • Implements tool-calling agents with guardrails
  • Adds evaluation, tracing and cost tracking
0%ready

Skill-gap analysis

Your live coverage of this path's tracks, from local progress.

Focus areas

Advanced PythonAsyncIOFastAPIPydanticHTTP clientsLLM APIsStructured outputTool callingEmbeddingsRAGAgentsEvaluationObservabilityLLM gateways

Skill prerequisites

asynciofastapi