Your question is Inference Pipeline for ML Models. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
How would you build an inference pipeline (for serving ML models)?
Asked in the Role Related Knowledge (RRK) stage. This was part of a series of technical RRK questions, and the interviewer expected detailed answers. A reported follow-up was: What are the differences in infrastructure required (for different inference setups)?
