• ML sys design problems cover real life scenarios — design a video recommendation service, ads ranking system, search query classifier etc.
  • The interviewer is looking for both breadth and depth. In breadth the focus is on your understanding of end-to-end ML lifecycle. For evaluating your expertise, (depth), interviewers go deep into the weeds of one or a few areas in ML lifecycle such as training, evaluation, deployment etc.
  • Here’s a way to structure your end-to-end ML lifecycle part.

--

--