Remote Ai Safety Red Teamer — Frontier Model Stress Tests

Mercor is seeking an AI Safety Red Teamer for a remote, contract role. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks and unsafe behaviors, and help improve safety posture through rigorous evaluation.

You will document vulnerabilities, contribute to benchmarking, and collaborate with researchers to advance model alignment and robustness. Requires 5+ years in AI safety or related fields and a strong track record in prompt design and analysis.