Remote AI Safety Red Teamer

mercor; San Francisco (CA); Hybrid; GBP 73,000 - 87,000; Part time

Job summary

Mercor is seeking an AI Safety Red Teamer on a remote, contract basis. You will design adversarial prompts to stress-test frontier AI models and identify jailbreaks, unsafe behaviors, hallucinations, and policy failures.

You will evaluate model robustness across domains such as misinformation, cyber, biosecurity, fraud, and political content, and document vulnerabilities while contributing to safety benchmarking and red-teaming reports.

Qualifications

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

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.

Skills

Analytical reasoning

Prompt design

Written communication

Education

Bachelor’s degree in related field

Job description

Mercor is seeking an AI Safety Red Teamer on a remote, contract basis. You will design adversarial prompts to stress-test frontier AI models and identify jailbreaks, unsafe behaviors, hallucinations, and policy failures.

You will evaluate model robustness across domains such as misinformation, cyber, biosecurity, fraud, and political content, and document vulnerabilities while contributing to safety benchmarking and red-teaming reports.