Remote AI Safety Red Teamer - Adversarial Testing

Mercor; Madrid; Presencial; EUR 84.000 - 100.000; A tiempo parcial

Descripción de la vacante

Mercor is seeking an AI Safety Red Teamer for remote engagement. 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 domains like misinformation, cyber, biosecurity, fraud, political content, and other sensitive areas, documenting vulnerabilities and contributing to safety benchmarking and red-teaming reports.

Formación

• Bachelor's degree or higher in a related discipline.
• 5+ years of professional experience in AI Safety or 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.

Conocimientos

Analytical reasoning

Prompt design

Written communication

Adversarial prompts design

Educación

Bachelor’s degree or higher in relevant field

Descripción del empleo

Mercor is seeking an AI Safety Red Teamer for remote engagement. 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 domains like misinformation, cyber, biosecurity, fraud, political content, and other sensitive areas, documenting vulnerabilities and contributing to safety benchmarking and red-teaming reports.