Mercor is assembling a remote red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data that strengthens customer AI systems. The work is text-based and designed to be safety-focused with clear guidelines and wellness resources.
You will review AI outputs touching on sensitive topics like bias or misinformation, annotate and classify findings, and document reproducible artifacts for customers to act on.
#J-18808-Ljbffr
Remote AI Adversarial Red Team Engineer employer: Obsidian
Obsidian is an exceptional employer located in the vibrant Greater London area, offering a dynamic work culture that fosters innovation and collaboration among experts in the field. Employees benefit from a fast-start program with opportunities for growth and extension, alongside a commitment to quality in AI model training that makes a meaningful impact in genomics. With a focus on professional development and a supportive environment, Obsidian is dedicated to empowering its team members to excel in their careers.
