Frontier AI Safety Red Teamer

Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high-risk topics.

Responsibilities include designing prompts, identifying jailbreaks and unsafe behaviours, and documenting vulnerabilities for safety benchmarking and red-teaming reports, collaborating with researchers to improve alignment and safety.

This is a strong opportunity to take on the Frontier AI Safety Red Teamer role at Mercor.

For the Frontier AI Safety Red Teamer position at Mercor, we are reviewing applications now.

Step into the Frontier AI Safety Red Teamer role at Mercor in New York, NY, United States and grow with us.

Please review the full job details above before applying.