Remote AI Safety Red Teamer: Adversarial Testing

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

Job summary

Mercor is seeking an AI Safety Red Teamer for a remote, contract role. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks and unsafe behaviors, and help improve safety posture through rigorous evaluation.

You will document vulnerabilities, contribute to benchmarking, and collaborate with researchers to advance model alignment and robustness. Requires 5+ years in AI safety or related fields and a strong track record in prompt design and analysis.

Qualifications

• Bachelor's degree or higher in a related field such as CS, cybersecurity, journalism, or policy.
• 5+ years of professional experience in AI Safety, red teaming, 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, and policy failures.
• Evaluate model robustness across misinformation, cyber, biosecurity, and more.
• 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

Analytical reasoning

Written communication

Education

Bachelor's degree or higher

Job description

Mercor is seeking an AI Safety Red Teamer for a remote, contract role. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks and unsafe behaviors, and help improve safety posture through rigorous evaluation.

You will document vulnerabilities, contribute to benchmarking, and collaborate with researchers to advance model alignment and robustness. Requires 5+ years in AI safety or related fields and a strong track record in prompt design and analysis.