Coach note

Interviewers ask this kind of question to surface how you think, not what you remember. The strongest answers are specific, calmly told, and end on what changed.

ML system design · Serving architecture

Your search ranking model serves results in under 50ms, but you want to add a large language model reranker. Design the serving architecture to maintain latency SLAs.

Type your answer

0of ~140 wordsAbout a minute spoken

Voice isn’t supported in this browser — type your answer in the box.

Create a free account to get more critiques.

Your answer

Your answer appears here as you speak.

Your search ranking model serves results in under 50ms, but you want to add a large language model reranker. Design the serving architecture to maintain latency SLAs.

Practice more