Offline the model scores 0.86 AUC. Served live, it's effectively random. Walk me through training/serving skew.
The most expensive bug class in production ML: two implementations of 'the same' feature that quietly disagree. The diagnostic that finds it in an afternoon, and the architecture that makes it impossible.
Updated Sep 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.
The most expensive bug class in production ML: two implementations of 'the same' feature that quietly disagree. The diagnostic that finds it in an afternoon, and the architecture that makes it impossible.
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.
