Remote AI Safety Red Teamer — Frontier Robustness Expert

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

Job summary

Mercor is seeking an AI Safety Red Teamer for a contract role to stress-test frontier AI models remotely, with compensation of $70–$84 per hour. You will design adversarial prompts, identify jailbreaks and policy failures, and help with safety benchmarking and reports.

Ideal candidates have 5+ years in AI safety or related fields, strong analytical and written communication skills, and experience in prompt design for frontier AI systems. Collaboration with researchers is key.

Qualifications

• Bachelor's degree or higher in a related discipline.
• 5+ years in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity or related field.
• Strong analytical reasoning, prompt design, and written communication.
• Experience designing adversarial prompts for frontier AI systems.

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, and political content.
• Document vulnerabilities and contribute to safety benchmarking and red-teaming reports.
• Collaborate with AI researchers to improve model alignment, robustness, and safety.

Skills

Adversarial prompts

Prompt design

Analytical reasoning

Written communication

Education

Bachelor's degree

AI Safety field

Cybersecurity background

Public Policy

Job description

Mercor is seeking an AI Safety Red Teamer for a contract role to stress-test frontier AI models remotely, with compensation of $70–$84 per hour. You will design adversarial prompts, identify jailbreaks and policy failures, and help with safety benchmarking and reports.

Ideal candidates have 5+ years in AI safety or related fields, strong analytical and written communication skills, and experience in prompt design for frontier AI systems. Collaboration with researchers is key.