Go from AI user to AI engineer
Structured curriculum covering LLM internals, RAG, prompt engineering, fine-tuning, agents, and production deployment — with code examples throughout.
What's inside
ML & LLM Foundations
Transformer architecture, attention math, tokenization, inference optimization, MoE models — everything you need to reason about LLMs at the engineering level.
LLM Engineering
RAG pipelines, prompt engineering, fine-tuning with LoRA/QLoRA, agents and tool-calling, context window management, and structured output extraction.
Production AI
Evaluation frameworks, cost optimization, observability, safety and guardrails, deployment patterns, and vector database selection — shipping AI to real users.
Free open guides
No account neededAll categories
How it works
Browse the open guides — no account required
Sign up and pick your learning path
Work through topics in order: Beginner → Advanced
Study code examples and common mistakes
Practice interview questions for each topic
Ready to become an AI engineer?
74+ topics structured from Python basics to deploying production LLM systems. Start with 5 free guides — no account required.