Skip to content

AI Engineering Resources

A curated collection of the most valuable open-source repositories, video series, technical blogs, and essential books for mastering AI engineering — from foundational deep learning to production agents and LLM serving.

⭐️ Top GitHub Repositories

Repository Focus Area Description
vLLM LLM Serving High-throughput, memory-efficient LLM inference engine with PagedAttention.
LiteLLM API Gateway Call 100+ LLM APIs using a standardized OpenAI format with cost tracking and fallbacks.
LangGraph Agent Framework Build stateful, multi-agent workflows with cyclic graphs and human-in-the-loop controls.
Smolagents Code Agents Lightweight library from Hugging Face for building agents that execute Python code actions.
LlamaIndex RAG & Data Data framework to connect private data sources (PDFs, DBs, APIs) to LLMs.
AutoGen Multi-Agent Framework by Microsoft enabling multi-agent conversation and task orchestration.
DSPy Prompt Optimization Programmatically optimize LM prompts and module weights instead of manual prompting.
Instructor Structured Outputs Extract structured data (JSON matching Pydantic schemas) reliably from LLMs.
Ragas RAG Evals Framework for evaluating Retrieval Augmented Generation pipelines with metrics.
Triton GPU Kernel Programming Open-source Python-like programming language and compiler for writing custom GPU kernels.

🎬 Must-Watch Videos & Courses

📰 Blogs & Newsletters

  • Chip Huyen's Blog
    In-depth articles on ML systems design, real-time machine learning, and moving AI from prototype to production.
  • Eugene Yan's Blog
    Practical guides on LLM patterns, search/recommendation systems, evals, and real-world AI engineering tradeoffs.
  • Lilian Weng (Lil'Log)
    Comprehensive technical synthesis of research frontiers including autonomous agents, RLHF, and prompt engineering.
  • Anthropic Research & Engineering
    Insights into constitutional AI, interpretability, prompt design, and system architecture behind Claude.
  • OpenAI Cookbook
    Hands-on recipes, code snippets, and integration guides for common LLM application patterns.
  • Ahead of AI (Sebastian Raschka)
    Clear, breakdown articles explaining recent AI papers, fine-tuning techniques, and model architectures.

📚 Essential Books

  • Designing Machine Learning Systems (Chip Huyen)
    The standard textbook for data engineering, model monitoring, deployment pipelines, and system trade-offs.
  • Build a Large Language Model From Scratch (Sebastian Raschka)
    Step-by-step tutorial implementing every component of a Transformer LLM from tokenization to instruction tuning.
  • Deep Learning (Ian Goodfellow, Yoshua Bengio, Aaron Courville)
    The foundational reference for mathematical theory, optimization, and neural network fundamentals.
  • Hands-On Machine Learning (Aurélien Géron)
    Practical introduction to standard ML workflows, Scikit-Learn, PyTorch, and model evaluation.

🔗 Handbook Reference Indexes