Remote AI Safety Red Teamer - Frontier Model Stress Tests

mercor; Denmark; Remote; DKK 643,000 - 772,000; Full time

Job summary

Mercor is seeking an AI Safety Red Teamer to stress-test frontier AI models through adversarial prompts, jailbreak testing, and robustness evaluations. This remote contract role demands deep expertise in AI safety and strong written communication.

You will document vulnerabilities, contribute to safety benchmarking, and collaborate with researchers to improve model alignment and safety across sensitive domains.

Qualifications

• Bachelor's degree or higher in CS, cybersecurity, journalism, communications, psychology, biology, chemistry, public policy or related field.
• 5+ years 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

Analytical reasoning

Prompt design

Written communication

AI safety experience

Education

Bachelor's degree or higher in CS / Cybersecurity / related field

Job description

Mercor is seeking an AI Safety Red Teamer to stress-test frontier AI models through adversarial prompts, jailbreak testing, and robustness evaluations. This remote contract role demands deep expertise in AI safety and strong written communication.

You will document vulnerabilities, contribute to safety benchmarking, and collaborate with researchers to improve model alignment and safety across sensitive domains.