Remote AI Safety Red Teamer: English & Portuguese

Mercor is seeking AI Safety Experts to test and harden conversational AI systems. You will work remotely to simulate jailbreaks, prompt injections, and misuse cases to uncover weaknesses and document findings for clients.

The role requires native English and Portuguese, strong communication, and prior red-teaming or cybersecurity experience. You will contribute to risk assessments and craft high-quality data and reports for global labs.