Your question is Design ML Video Processing Pipeline. 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).
You're planning a pipeline that takes uploaded video, runs machine learning over it, and makes the results available to downstream applications. You want to think through how ingestion, processing, model execution, and delivery should fit together before implementation.
How would you architect a pipeline for video processing that incorporates machine learning models?