Mercor is assembling a panel of nuclear domain experts in Greater London to red-team frontier AI models. The aim is to test whether a model can correctly judge misuse potential by answering legitimate questions fully while refusing dangerous ones.
You will write prompts across benign, dual-use, and adversarial categories, evaluate model responses, and draft the reference answer with technical reasoning. This is a writing-intensive, policy-focused role requiring clear rationale for every judgment.
#J-18808-Ljbffr
Nuclear AI Safety Red-Teaming Engineer in London 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.
