There is more of this guide.
Practice
14 questions- ML system designDesign an ML system to recommend videos to logged-in users on a streaming service with 200 million users.
- ML system designDesign a feature store for a company with a hundred ML use cases. What's non-negotiable in the design?
- ML system designDesign the labeling pipeline for a system that classifies user-uploaded images into 200 categories. Labels are noisy.
- ML system designDesign the data pipeline for training a delivery-time prediction model that needs to update daily.
- ML system designHow would you architect a system that lets data scientists run dozens of experiments per day against the same offline dataset, reproducibly?
- ML system designYou discover that the feature store generates one set of values offline and a slightly different one online. How do you design around that?