Remote AI Red Team Specialist - Safety Adversarial Testing

Mercor is building a remote red team for AI safety, focusing on adversarial testing of conversational models and data generation to surface vulnerabilities. The role involves rigorous, structured testing with clear documentation and reproducible outcomes, across diverse projects and clients.

We value candidates with prior red-teaming experience, strong analytical thinking, and excellent communication skills to explain risks to both technical and non-technical stakeholders.

#J-18808-Ljbffr