AI Safety Red Teamer

Lead adversarial testing of frontier AI systems to expose vulnerabilities, design challenging prompts, and evaluate model behavior on complex, high-risk, and ambiguous topics. This role focuses on finding jailbreaks, unsafe behavior, hallucinations, and policy failures across sensitive domains so researchers can improve model alignment and robustness.

• Design adversarial prompts and scenarios to stress-test frontier AI models.
• Identify jailbreaks, unsafe behaviors, hallucinations, and failures to follow policy or alignment constraints.
• Evaluate model robustness in domains including misinformation, cyber, biosecurity, fraud, political content, and other sensitive or grey-area topics.
• Document discovered vulnerabilities and contribute findings to safety benchmarking and red-teaming reports.
• Collaborate with AI researchers to inform improvements to model alignment, robustness, and safety mitigations.

Required

• 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 and 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.

Preferred

• Experience with AI Red Teaming, Reinforcement Learning from Human Feedback, Supervised Fine Tuning, AI Alignment, or Trust and Safety work.
• Familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies.
• Domain expertise in one or more grey-area topics such as cyber, biosecurity, political content, misinformation, or scientific safety.

• Location: Remote
• Employment type: hourly

• 70 - 84 hourly

• Contribute directly to securing and strengthening next-generation frontier AI models.
• Work on cutting-edge adversarial testing alongside AI researchers and safety teams.
• Influence how AI systems respond to complex, real-world safety challenges.