AI Safety Red Teamer — Adversarial Testing

Mercor is seeking an AI Safety Red Teamer to stress-test frontier AI models through adversarial prompts and vulnerability assessment. This remote contract role demands deep expertise in AI safety, red teaming, and written communication to report findings clearly.

Responsibilities include identifying jailbreaks and safety failures, evaluating model robustness across sensitive domains, and collaborating with researchers to improve alignment and safety benchmarks.