AI Safety Red Teamer — Adversarial Prompt Expert (Remote)

Mercor; Dublin; Remote; EUR 84,000 - 101,000; Part time

Job summary

Mercor seeks an AI Safety Red Teamer for a remote contract role to stress-test frontier AI systems and uncover vulnerabilities. Compensation is $70–$84 per hour, with work conducted remotely.

The successful candidate will design adversarial prompts, identify jailbreaks and unsafe behaviors, evaluate model robustness across domains, and document findings for safety benchmarking, collaborating with AI researchers to improve alignment and safety.

Qualifications

• 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.

Responsibilities

• Design adversarial prompts to stress-test frontier AI models.
• Identify jailbreaks, unsafe behaviors, hallucinations, and policy failures.
• Evaluate model robustness across misinformation, cyberbiosecurity, 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

AI safety

Prompt evaluation

Written communication

Education

Bachelor's degree

Job description

Mercor seeks an AI Safety Red Teamer for a remote contract role to stress-test frontier AI systems and uncover vulnerabilities. Compensation is $70–$84 per hour, with work conducted remotely.

The successful candidate will design adversarial prompts, identify jailbreaks and unsafe behaviors, evaluate model robustness across domains, and document findings for safety benchmarking, collaborating with AI researchers to improve alignment and safety.