Remote AI Safety Red Teamer — Frontier Model Vetting

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

Job summary

Mercor is seeking an AI Safety Red Teamer for a remote contract position. The role focuses on stress-testing frontier AI models, identifying jailbreaks and unsafe behaviors, and evaluating robustness across sensitive domains.

The ideal candidate has 5+ years in AI safety or related fields, strong analytic reasoning, and experience with adversarial evaluation. Collaboration with researchers is essential to improve alignment and safety.

Qualifications

• Bachelor's degree or higher in a related discipline is required.
• 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety or related fields.
• Excellent analytic 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 behaviors, hallucinations, and policy failures.
• Evaluate model robustness across misinformation, cyber, biosecurity, fraud, and political content.
• 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

Analytical reasoning

Written communication

AI safety

Adversarial testing

Education

Bachelor's degree or higher in Computer Science

Bachelor's degree or higher in Cybersecurity

Bachelor's degree or higher in Journalism

Bachelor's degree or higher in Public Policy

Job description

Mercor is seeking an AI Safety Red Teamer for a remote contract position. The role focuses on stress-testing frontier AI models, identifying jailbreaks and unsafe behaviors, and evaluating robustness across sensitive domains.

The ideal candidate has 5+ years in AI safety or related fields, strong analytic reasoning, and experience with adversarial evaluation. Collaboration with researchers is essential to improve alignment and safety.