Remote AI Safety Red Teamer — Adversarial Prompt Architect

mercor; España; Remote; EUR 86,000 - 103,000; Part time

Job summary

Mercor is seeking an AI Safety Red Teamer for a remote contract role. You will design adversarial prompts to stress-test frontier AI models and identify unsafe behaviors, jailbreaks, and policy failures. You will evaluate robustness across domains such as misinformation, cyber, biosecurity, and political content.

Applicants should have 5+ years in AI Safety or related fields, strong analytical and written communication skills, and a background in related disciplines.

Qualifications

• 5+ years of professional experience in AI Safety or related field.
• Experience designing adversarial prompts or evaluating frontier AI systems.
• Strong analytical reasoning and written communication skills.

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, 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.

Skills

Adversarial prompt design

Prompt evaluation

Analytical reasoning

Written communication

Education

Bachelor’s degree or higher in Computer Science or related field

Tools

AI safety

Job description

Mercor is seeking an AI Safety Red Teamer for a remote contract role. You will design adversarial prompts to stress-test frontier AI models and identify unsafe behaviors, jailbreaks, and policy failures. You will evaluate robustness across domains such as misinformation, cyber, biosecurity, and political content.

Applicants should have 5+ years in AI Safety or related fields, strong analytical and written communication skills, and a background in related disciplines.