Remote AI Safety Red Teamer - Stress-Test Frontier Models

Mercor; Lisboa; Presencial; EUR 83 000 - 100 000; Tempo integral

Resumo da oferta

Mercor connects elite creative and technical talent with leading AI research labs. Remote contractor role as AI Safety Red Teamer designing adversarial prompts to stress-test frontier AI models.

You will identify jailbreaks, unsafe behaviors, and policy failures, and evaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains. Collaboration with AI researchers to improve safety.

Qualificações

• Bachelor's degree or higher in a related discipline.
• 5+ years of professional AI Safety or related field experience.
• Strong analytical reasoning, prompt design, and written communication skills.
• Experience designing adversarial prompts or evaluating frontier AI systems.

Responsabilidades

• 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.

Conhecimentos

Analytical reasoning

Prompt design

Written communication

Adversarial prompt design

Formação académica

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

Descrição da oferta de emprego

Mercor connects elite creative and technical talent with leading AI research labs. Remote contractor role as AI Safety Red Teamer designing adversarial prompts to stress-test frontier AI models.

You will identify jailbreaks, unsafe behaviors, and policy failures, and evaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains. Collaboration with AI researchers to improve safety.