AI Engineer Notebooks
A set of runnable Colab notebooks that teach the applied AI Engineer / Forward Deployed Engineer skill set, including model APIs, RAG, evals, agents and fine-tuning, built from raw API calls instead of a framework, and run on the free Groq API.
AI Engineer Notebooks is a collection of self-contained Colab notebooks for engineers moving into AI Engineer, Forward Deployed Engineer, Applied AI or Solutions Engineer roles. Each notebook installs its own dependencies, reads API keys from Colab secrets, and ends with exercises, and the notebooks are meant to be worked through in order.
The material is deliberately framework-free: readers write the agent loop, retrieval-augmented generation and evaluation code from raw API calls before reaching for a library such as LangChain or LlamaIndex, so they understand what the wrapper is doing. Evaluation is treated as a running habit rather than a final step, and three case studies, a support assistant, a pipeline-versus-agent cost comparison, and a red-team robustness benchmark, apply the skills together.
Everything runs on the free Groq API; the two exercises Groq cannot host, fine-tuning and self-hosted serving, are concept-first with optional Colab GPU appendices.