Your hiring model never sees gender, and it still discriminates. How do you find and remove proxy features?
Dropping the protected attribute is the answer most candidates give, and it accomplishes nothing: the attribute is reconstructible from the features you kept. Here is how to actually locate the proxies and what removing them costs you.
Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.
Dropping the protected attribute is the answer most candidates give, and it accomplishes nothing: the attribute is reconstructible from the features you kept. Here is how to actually locate the proxies and what removing them costs you.
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.
