Continuous ETA model retraining pipeline
Design a continuous (automated) retraining pipeline for a food-delivery ETA model that must adapt to changing conditions — new restaurants, traffic patterns, weather, seasonality. The model should retrain regularly on fresh data with no human in the loop for routine retrains, but a bad model must never auto-deploy. Design the pipeline from raw data to a safely-promoted production model, and explain the gates that prevent a corrupted dataset or a regressed model from shipping automatically.
What a strong answer looks like
Clarify scale and constraints first. Propose a clean component breakdown, then go deep on the hard parts (data model, bottlenecks, consistency, failure modes) and name the trade-offs you are making.
Clarify4:30 left
Estimate4:30 planned
Design13:30 planned
Deep dive10:30 planned
Failure7:00 planned
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.