Remote AI Safety Red Team Expert (Adversarial ML)

Mercor is building a red team for AI safety. This role involves testing conversational AI models with jailbreaks, prompt injections, and bias exploration. Work is remote and text-only, with clear guidelines and wellness support.

You will annotate failures, classify vulnerabilities, and document reproducible attack cases and reports to help customers strengthen their systems. Excellent language judgment and structured, guideline-driven work are essential.