Frontier AI Safety Red Team Specialist

Mercor in Paris seeks 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, ambiguous topics, collaborating with researchers to improve alignment and safety.

The role emphasizes rigorous prompt design, vulnerability documentation, and cross-disciplinary teamwork to strengthen model robustness and safety.