Descripción de la oferta
Mercor is seeking an AI Safety Specialist to work remotely on adversarial prompt design and safety evaluation for frontier AI systems. You will identify harmful outputs, assess jailbreaks, and document vulnerabilities to improve alignment and robustness. Ideal candidates have a strong background in AI safety, trust & safety, or related fields, plus 5+ years of experience and a degree in CS or a related discipline. This is a contract, remote engagement with competitive hourly compensation. #J-18808-Ljbffr
