Frontier AI Safety Red Teamer

mercor; San Francisco (CA); Hybrid; GBP 73,000 - 87,000; Part time

Job summary

Mercor is seeking aContract AI Safety Red Teamer to stress-test frontier AI models from a remote position. You will design adversarial prompts, identify jailbreaks and unsafe behaviors, and evaluate model robustness across sensitive domains.

The role requires 5+ years in AI safety or red teaming, strong analytical reasoning, and excellent written communication. Collaboration with AI researchers will drive improved model alignment and safety measures.

Qualifications

• Requires a degree in a relevant field and 5+ years in AI safety or red teaming.
• Strong ability to design adversarial prompts and assess model safety.
• Excellent written communication and analytical reasoning.

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 engineering

Analytical reasoning

Written communication

Education

Bachelor's degree or higher

Related disciplines

Job description

Mercor is seeking aContract AI Safety Red Teamer to stress-test frontier AI models from a remote position. You will design adversarial prompts, identify jailbreaks and unsafe behaviors, and evaluate model robustness across sensitive domains.

The role requires 5+ years in AI safety or red teaming, strong analytical reasoning, and excellent written communication. Collaboration with AI researchers will drive improved model alignment and safety measures.