Frontier AI Safety Red Team Expert

Mercor; København; On-site; DKK 900,000 - 1,500,000; Full time

Job summary

Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate behavior across high-risk, ambiguous topics.

Responsibilities include stress-testing models with jailbreak prompts, documenting vulnerabilities, and contributing to safety benchmarking and red-teaming reports.

Qualifications

• Experience designing adversarial prompts or evaluating frontier AI systems.
• Strong analytical reasoning and written communication skills.
• 5+ years in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, or related field.

Responsibilities

• Design adversarial prompts to stress-test frontier AI models.
• Identify jailbreaks, unsafe behaviours, 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

Adversarial testing

Prompt design

Model evaluation

Analytical reasoning

Written communication

Education

Bachelor's degree or higher (CS/Cybersecurity/related)

Tools

AI safety tooling

Job description

Mercor is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate behavior across high-risk, ambiguous topics.

Responsibilities include stress-testing models with jailbreak prompts, documenting vulnerabilities, and contributing to safety benchmarking and red-teaming reports.