Location: Remote

Salary: $$$/bug

Type: Contract

AfterQuery (YC W25) is hiring software engineers to help build the most advanced evaluation benchmark for frontier AI coding models. We’re partnering with a leading foundation model lab to develop Project Bug, a new coding benchmark designed to test models' ability to understand, reason through, and fix realistic code errors. AfterQuery (YC W25) is hiring senior software engineers to help build the most advanced evaluation benchmark for frontier AI coding models. We’re partnering with a leading foundation model lab to develop Project Bug, a new coding benchmark designed to test models' ability to understand, reason through, and fix realistic code errors.

In this role, you will design bugs that appear in real-world coding workflows - the kind of subtle, production-grade bugs that would trip up any junior dev. You’ll then test those bugs with the best models in the world. If the models fail and your fix is valid, you get paid. Role starts ASAP.

Apply Now