Remote AI Safety Red Teamer - Adversarial Prompt Expert

Mercor seeks an AI Safety Red Teamer to design adversarial prompts and stress-test frontier AI models from a remote setting. The role focuses on identifying jailbreaks, unsafe behaviors, and policy failures while evaluating robustness across sensitive domains.

You will document vulnerabilities and contribute to safety benchmarks and reports. The ideal candidate has 5+ years in AI Safety or related fields, strong analytical and written communication skills, and experience in AI red teaming, RLHF,