AI Safety Red Teamer - Remote Contract

Mercor; Helsinki; On-site; EUR 83,000 - 100,000; Part time

Job summary

Mercor, a connector of elite creative and technical talent with leading AI research labs, invites an AI Safety Red Teamer to join on a contract basis. This remote role requires a strong background in AI safety, red teaming, and adversarial testing, with 5+ years in related fields.

Compensation ranges from $70 to $84 per hour, with collaboration across research teams. If you design adversarial prompts and document vulnerabilities, you will help benchmark safety and strengthen model alignment.

Qualifications

• Bachelor's degree or higher in CS, cybersecurity, journalism, or related field.
• 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or 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, 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

Prompt design

AI safety

Analytical reasoning

Written communication

Education

Bachelor's degree or higher

Job description

Mercor, a connector of elite creative and technical talent with leading AI research labs, invites an AI Safety Red Teamer to join on a contract basis. This remote role requires a strong background in AI safety, red teaming, and adversarial testing, with 5+ years in related fields.

Compensation ranges from $70 to $84 per hour, with collaboration across research teams. If you design adversarial prompts and document vulnerabilities, you will help benchmark safety and strengthen model alignment.