Your model scores well offline but worse online, and you suspect training-serving skew. How do you find it?
Same model, two answers: clean offline, ugly online. The cause is almost always a feature computed differently across the two paths. Here is the diff-based hunt that localizes it to a single column.
Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.
Same model, two answers: clean offline, ugly online. The cause is almost always a feature computed differently across the two paths. Here is the diff-based hunt that localizes it to a single column.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
