Remote AI Benchmark Test Engineer

Mercor, a leading AI platform, seeks a QA/test engineer to join its GenAI benchmarking effort. You will design checks, review tasks, and debug environments, ensuring edge cases are covered and results are robust.

This is a full-time W-2 role placed with Cincinnatus LLC, fully remote in the United States. You will work about 35 hours per week, collaborating with researchers and task authors to build repeatable quality processes and clear documentation, with independence to tackle ambiguous