Remote AI Safety Red Teamer — Frontier Model Stress Tests

mercor; Portugal; Remote; EUR 86,000 - 103,000; Full time

Job summary

Mercor seeks an AI Safety Red Teamer to join a contract-based engagement focused on stress-testing frontier AI systems. This remote role collaborates with researchers to identify vulnerabilities and advance safety benchmarks in diverse domains.

The ideal candidate has 5+ years in AI safety or related fields, strong prompt-design skills, and excellent written communication. Prior experience with adversarial testing is highly valued for robust evaluations in dynamic environments.

Qualifications

• Bachelor's degree or higher in CS, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy or related field.
• 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or related field.
• 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

Prompt design

AI Safety

Analytical reasoning

Written communication

Adversarial prompts

Education

Bachelor's degree or higher

Job description

Mercor seeks an AI Safety Red Teamer to join a contract-based engagement focused on stress-testing frontier AI systems. This remote role collaborates with researchers to identify vulnerabilities and advance safety benchmarks in diverse domains.

The ideal candidate has 5+ years in AI safety or related fields, strong prompt-design skills, and excellent written communication. Prior experience with adversarial testing is highly valued for robust evaluations in dynamic environments.