Remote AI Safety Red Team Specialist

Mercor invites a human data expert to remotely probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data that enhances AI safety. You will annotate failures, classify vulnerabilities, and follow playbooks to keep testing consistent.

Clear documentation and reproducible attack cases will be produced for customer use. Native English and Odia fluency are required, with the ability to explain reasoning to diverse audiences.