epochs

Paths · 9 modules · 50 lessons · 4 projects · about 18 hours

Applied LLM Engineer

Make a model excellent at one job: prompting, retrieval, fine-tuning and rigorous evaluation.

Who it's for

Engineers who already call LLM APIs and want to go deeper on quality.

By the end, you can
  • Choose between prompting, retrieval and fine-tuning with evidence
  • Fine-tune with LoRA on a well-built dataset
  • Prove a change helped with a proper evaluation

The route

Modules in order, with a project after the lessons it builds on. Mark lessons as done and tick project steps, and this page tracks your progress. Sign in to keep it on every device.

  1. Module 05 · 4 lessons · about 18 minTokens and embeddingsHow text becomes numbers a model can work with.Not started
  2. Module 06 · 6 lessons · about 26 minTransformersAttention, the full architecture, and how the next token is chosen.Not started
  3. Module 08 · 6 lessons · about 24 minPrompting and contextPrompts, structured outputs, tools, and what to put in the window.Not started
  4. Module 09 · 5 lessons · about 21 minSearch and retrievalRAG from chunking to reranking, and how to evaluate it.Not started
  5. Project · Intermediate · 4–6 hours · ProChat with your documentsBuild retrieval-augmented generation end to end: chunking, retrieval, a grounded prompt, citations and an evaluation.6 steps
  6. Module 04 · 3 lessons · about 11 minDeep learning in PyTorchTensors, autograd and training loops: the tools real ML work uses.Not started
  7. Module 07 · 8 lessons · about 29 minTraining and fine-tuningPretraining, LoRA, preference tuning and the data behind them.Not started
  8. Project · Advanced · 3–4 hours · ProFine-tune a language model with LoRATeach a real language model a new style by training less than 0.2% of its weights, on a laptop CPU.5 steps
  9. Module 11 · 5 lessons · about 16 minEvaluationDecide what good means, then measure it without fooling yourself.Not started
  10. Project · Intermediate · 3–4 hours · ProAn evaluation harnessBuild the tool every AI team needs: run a fixed test set, see what passed, and know whether a change really helped.5 steps
  11. Module 12 · 6 lessons · about 19 minInference and servingWhere the time goes, and how to make models fast and cheap.Not started
  12. Module 13 · 7 lessons · about 21 minProduction AI and MLOpsRouting, fallbacks, budgets, monitoring and safety in real systems.Not started
  13. Project · Intermediate · 2–3 hours · ProPut your project onlineTurn the notes search engine into a tested web API, package it with Docker, and give it a public address.6 steps