Remote AI Safety Red Teamer — Frontier Model Vetting

Mercor is seeking an AI Safety Red Teamer for a remote contract position. The role focuses on stress-testing frontier AI models, identifying jailbreaks and unsafe behaviors, and evaluating robustness across sensitive domains.

The ideal candidate has 5+ years in AI safety or related fields, strong analytic reasoning, and experience with adversarial evaluation. Collaboration with researchers is essential to improve alignment and safety.