Role OverviewMercor is seeking an AI Safety Red Teamer Expert to design adversarial prompts, identify vulnerabilities, and evaluate model robustness. The role involves collaborating with AI researchers to improve model alignment and safety. The ideal candidate has 5+ years of experience in AI Safety, AI Red Teaming, or a related field, and a strong analytical reasoning and written communication skills.
What You Will Do
Design adversarial prompts, identify jailbreaks, evaluate model robustness, document vulnerabilities, and contribute to safety benchmarking and red-teaming reports.
Why It Might Be a Fit
The ideal candidate has experience designing adversarial prompts, evaluating frontier AI systems, and expertise in one or more grey-area domains, including cyber, biosecurity, or scientific safety.
Requirements
- Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline.
- 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related field.
- Strong analytical reasoning, prompt design, and written communication skills.
- Experience designing adversarial prompts or evaluating frontier AI systems.
]]>