Build AI systems from first principles — not just use them.
A hands-on track for builders who want to understand how AI systems actually work under the hood. Start from tensors and autograd, build a GPT from scratch, and ship a fine-tuned model behind your own streaming API.
From a single neuron to a deployed, monitored ML service. 100 challenges covering the full supervised learning lifecycle.
Bridge from advanced ML to transformer-based AI systems. Embeddings, RAG, agents, eval, and production AI APIs — 100 challenges.
Fine-tuning, quantization, and production deployment of large language models. For engineers who want to go beyond API calls.
100 challenges, from a scalar gradient to a fine-tuned model streaming behind your own API.
Hands-on, single-GPU fine-tuning: adapt an open model to your task with LoRA/QLoRA, evaluate it honestly against the base, then quantize and self-host it behind your own OpenAI-compatible API. Free-tier and Colab friendly throughout.