Frontier AI Safety Red Teamer

Mercor; Amsterdam; Remote; EUR 95,000 - 140,000; Full time

Job summary

Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high-risk topics.

Responsibilities include stress-testing models, identifying unsafe behaviours, and documenting vulnerabilities to contribute to safety benchmarking. You will collaborate with researchers to improve alignment and robustness.

Qualifications

• Candidates must hold a degree or higher in a relevant field.
• Proven experience in AI safety, red teaming, or trust & safety.
• Strong analytical reasoning and clear written communication.
• Experience designing adversarial prompts or evaluating frontier AI systems.

Responsibilities

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

Skills

Adversarial prompt design

Jailbreak testing

Model evaluation & safety auditing

Analytical reasoning

Written communication

Frontend AI safety domain knowledge

Education

Bachelor's degree or higher in Computer Science or related

Job description

Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high-risk topics.

Responsibilities include stress-testing models, identifying unsafe behaviours, and documenting vulnerabilities to contribute to safety benchmarking. You will collaborate with researchers to improve alignment and robustness.