Data Science Interview Prep¶
A single entry point into seven self-contained study sites. Each one is a standalone knowledge base built for interview revision — pick a track below and you'll be routed into its own site, with a ← Study Hub link to come back here.
-
Mathematics
Probability, inferential statistics, and linear algebra for machine learning — the mathematical groundwork everything else builds on.
-
Classical ML
Linear models, trees, ensembles, unsupervised learning, and evaluation metrics — the classical machine learning foundation, end to end.
-
Deep Learning
Neural network mechanics, gradient flow, optimization, losses, CNNs, vision and generative models, and sequences with attention.
-
LLM Study Notes
Deep dives across the modern LLM stack: architecture, training, alignment, PEFT, inference, serving, and the 2026 model landscape.
-
Agentic AI
RAG and retrieval, agent loops, LangGraph internals, protocols (MCP/A2A), evaluation, serving, and end-to-end agent system design.
-
ML System Design Case Studies
Twenty worked ML and GenAI system design case studies, each with a full interview transcript and a one-page whiteboard cheat sheet.
-
Productionizing ML
Production ML system design, data foundations, training, serving, the production loop, infrastructure, build-vs-buy, and a hands-on implementation masterclass.
How this hub works
Each card opens a separate MkDocs site served from a sub-folder of this one. They share the same theme but keep independent navigation and search. Use the back link in any sub-site's top nav to return here.