Your question is Pandas Pipeline for Latency Percentile. 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).
Given a dataset containing model inference results, write a Pandas script to clean missing values, normalize the output scores, and group the data by model version to calculate the 90th percentile of latency.