AI Safety Red Teamer at Mercor

AI Safety Red Teamer | $70–$84/hr | Worldwide Remote

Join a cutting-edge team dedicated to securing the next generation of frontier AI models. As an AI Safety Red Teamer, you will design adversarial tests, uncover model vulnerabilities, and help shape how AI systems respond to complex, real-world safety challenges.

Responsibilities

• Design adversarial prompts to stress-test frontier AI models and uncover weaknesses.
• Identify jailbreaks, unsafe behaviors, hallucinations, and policy failures.
• Evaluate model robustness across sensitive domains including misinformation, cybersecurity, biosecurity, fraud, and political content.
• Document vulnerabilities and contribute to safety benchmarking and red-teaming reports.
• Collaborate with AI researchers to improve model alignment, robustness, and overall safety.

Required Qualifications

• Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related field.
• 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related discipline.
• Strong analytical reasoning, prompt design, and written communication skills.
• Demonstrated experience designing adversarial prompts or evaluating frontier AI systems.

Preferred Qualifications

• Experience with AI Red Teaming, RLHF, SFT, AI Alignment, or Trust & Safety practices.
• Familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies.
• Domain expertise in cyber, biosecurity, political content, misinformation, or scientific safety.

Why Join?

• Work on meaningful, high-impact projects that directly influence AI safety at the frontier.
• Collaborate with leading AI researchers and safety teams on cutting-edge adversarial testing.
• Help define how AI systems handle the most complex and sensitive real-world scenarios.