Remote AI Safety Red Teamer — Stress-Test Frontier Models

Mercor is seeking an AI Safety Red Teamer for a remote contract role. The position focuses on stress-testing frontier AI models through adversarial prompts, identifying jailbreaks, unsafe behaviors, and policy failures.

You will evaluate robustness across domains like misinformation, cyber, biosecurity, and political content, document vulnerabilities, and contribute to red-teaming reports. Collaboration with researchers will improve alignment and safety.