Prep Room
HomeInterview SimulatorContestsYour JobsSalary negotiationUpskillResourcesConcept guidesResume
Concept guidesServing a model inside a latency budgetSenior

There is more of this guide.

Practice

13 questions
  • ML system designDesign a fraud-detection ML system that has to decide every transaction in under 100ms at 10K transactions per second.
  • ML system designDesign a system for serving large-language-model inference to a million daily users, balancing cost and latency.
  • ML system designDesign a search-ranking system that personalizes results per user using behavioral features. Latency budget is 50ms.
  • ML system designDesign a feature for showing AI-generated product descriptions on an e-commerce site. Quality and cost both matter.
  • ML system designDesign the serving infrastructure for a system that runs many small models — say, one per customer — economically.
  • ML system designDesign a system that uses ML to suggest replies in a messaging product, with privacy as a hard constraint.
All questions
HomeYour JobsResumeResources
© 2026 Prep Room·From California·AI can make mistakes.
LegalAboutInsightsContactYour privacy choices