Courses · A track, not a content library
From classical machine learning to deep learning to modern AI engineering. Each course slots into the same brick → wall → castle model, so everything you learn keeps compounding into the next.
The on-ramp. Modern LLM systems rebuilt from first principles; tokens, prompts, RAG, agents, evaluation, and production. The natural prerequisite to the Professional track.
The flagship. Where Fundamentals stops, Professional starts; advanced RAG, fine-tuning (LoRA / DPO), RAGAS, multimodal, LLMOps, cloud deployment, and AI safety.
The full classical ML track: regression, trees, gradient boosting, kernels, calibration, deployment. The math, the intuition, the production reps.
Neural networks from neurons to transformers. Backprop, optimizers, regularization, CNNs, RNNs, attention; built by hand before any framework.
Planner-executor loops, tool design, memory, multi-agent workflows, observability, cost control.
From CNNs to ViTs to multimodal LLMs; built brick by brick from first principles.
SFT, LoRA, DPO, reward modeling; when to do it, and how to do it without burning compute.
Prompt injection, jailbreaks, model + data exfil, defenses for production systems.