Academyby Code2Deploy
All courses
Advanced

LLMOps

Building and operating LLM and RAG systems that survive contact with real users.

What you'll be able to do

  • Build a RAG pipeline that answers from your own documents
  • Evaluate output quality with something better than reading samples
  • Control token cost and latency under real traffic
  • Add guardrails against prompt injection and data leakage

Modules

  1. 01
    LLMs for engineersTokens, context windows, temperature, streaming, model selection and the cost of each
  2. 02
    Prompting and evaluationStructured prompts, tool calling, eval sets, LLM-as-judge and where it misleads
  3. 03
    Retrieval-augmented generationChunking strategy, embeddings, hybrid search, reranking, citation and grounding
  4. 04
    Vector storespgvector, Qdrant, Milvus, index tuning, refresh strategy for changing documents
  5. 05
    Serving and scalingInference servers, GPU capacity, caching, batching, fallback between providers
  6. 06
    Safety, cost and observabilityPrompt injection, PII handling, output filtering, token accounting, tracing a bad answer

Capstone

Ship a production RAG assistant over a real document set, with evaluation, cost tracking, guardrails and an observable failure path.