Remote AI Safety Red Teamer — Stress-Test Frontier Models

mercor; Italia; Teletrabalho; EUR 178 223 000 - 215 096 000; Tempo parcial

Resumo da oferta

Mercor is seeking an AI Safety Red Teamer for a remote contract role. The position focuses on stress-testing frontier AI models through adversarial prompts, identifying jailbreaks, unsafe behaviors, and policy failures.

You will evaluate robustness across domains like misinformation, cyber, biosecurity, and political content, document vulnerabilities, and contribute to red-teaming reports. Collaboration with researchers will improve alignment and safety.

Qualificações

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

Adversarial prompts

AI safety

Red team

Prompt design

Written communication

Formação académica

Bachelor's degree in CS or related

Descrição da oferta de emprego

Mercor is seeking an AI Safety Red Teamer for a remote contract role. The position focuses on stress-testing frontier AI models through adversarial prompts, identifying jailbreaks, unsafe behaviors, and policy failures.

You will evaluate robustness across domains like misinformation, cyber, biosecurity, and political content, document vulnerabilities, and contribute to red-teaming reports. Collaboration with researchers will improve alignment and safety.