Mercor is building a remote AI safety red team focused on adversarial data testing and vulnerability discovery. You will test conversational AI models with jailbreaks, prompt injections, misuse scenarios, and document actionable findings for customers.
We value English and Swedish fluency, curiosity, structured testing, and the ability to communicate risks clearly to both technical and non-technical stakeholders. Join us in advancing AI safety and resilience.
#J-18808-LjbffrRemote AI Adversarial Specialist β Red Team & Safety employer: Mercor
At Mercor, we pride ourselves on fostering a dynamic and innovative work culture that empowers our employees to excel in their roles. As a Remote Backend Engineer, you'll enjoy the flexibility of working from anywhere while collaborating with cutting-edge AI technology, alongside opportunities for professional growth and development. Our commitment to competitive compensation and a supportive environment makes Mercor an exceptional employer for those seeking meaningful and rewarding work in the tech industry.