Remote AI Safety Red Teamer – Adversarial Testing

Mercor is seeking an AI Safety Red Teamer to join our remote team. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks and unsafe behaviors, and evaluate model robustness across misinformation, cyber, biosecurity, and political content.

You will document vulnerabilities, contribute to safety benchmarking and red-teaming reports, and collaborate with AI researchers to improve alignment, robustness, and safety.

#J-18808-Ljbffr

Full job description from WhatJobs. Apply for this role →