AI Safety Red Teamer Expert

Role Responsibilities

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

Qualifications

Must-Have

• A bachelor's degree or higher in a field such as Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or another related discipline.
• 5+ years of professional work in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a comparable area.
• Demonstrated strength in analytical reasoning, prompt design, and writing.
• Prior work creating adversarial prompts or assessing frontier AI systems.

Preferred

• Hands-on background with AI Red Teaming, RLHF, SFT, AI Alignment, or Trust & Safety.
• Working knowledge of jailbreak testing, prompt engineering, or other adversarial evaluation methods.
• Subject-matter depth in at least one grey-area domain, for example cyber, biosecurity, political content, misinformation, or scientific safety.

Application process

Submit your application through NorthStar. Employer screening may follow after submission.

Resources & Support

For employer questions, contact support@mercor.com.