Remote AI Safety Red Teamer: Stress-Test Frontier Models

Mercor; Paris; Sur place; EUR 83 000 - 100 000; Plein temps

Résumé du poste

Mercor is seeking an AI Safety Red Teamer to work remotely on high-stakes AI safety projects. 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 misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains, and document vulnerabilities while contributing to safety benchmarking and red-teaming reports.

Qualifications

• Bachelor's degree or higher in a relevant field is required.
• 5+ years of professional AI safety or red-teaming experience.
• Strong analytical reasoning and prompt-design abilities.
• Excellent written communication skills.

Responsabilités

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

Connaissances

Analytical reasoning

Prompt design

Written communication

Formation

Bachelor's degree or higher in CS, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or related discipline

Description du poste

Mercor is seeking an AI Safety Red Teamer to work remotely on high-stakes AI safety projects. 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 misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains, and document vulnerabilities while contributing to safety benchmarking and red-teaming reports.