ML systems are moving to real-time. This repo explains exactly how to do feature engineering on streaming data (tumbling windows, sliding windows). You need this for "real-time fraud detection" questions.

GitHub is the gold mine for free, community-driven interview prep. These repos provide structured frameworks and real-world case studies:

While the full book is a paid resource, several GitHub repositories provide supplementary notes, diagrams, and cheat sheets: junfanz1/Awesome-AI-Review - GitHub

: Contains a general framework for MLE interviews and a Machine Learning System Design Draft PDF that outlines key architectural components and pipeline engineering.

: Offline testing and debugging strategies.

While not strictly an interview book, Chip Huyen’s O'Reilly book is the bible for production ML. Interviewers often borrow concepts from Chapter 4 (Training Data) and Chapter 8 (Monitoring).