Frontier AI Safety Red Teamer

Mercor; Zürich; Remote; CHF 120.000 - 170.000; Vollzeit

Zusammenfassung

Mercor seeks 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 AI behavior across high-risk, ambiguous topics.

Responsibilities include stress-testing models, identifying jailbreaks and policy failures, and documenting vulnerabilities for safety benchmarking. Collaboration with AI researchers will drive improvements in alignment and safety.

Qualifikationen

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

Aufgaben

• 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.

Kenntnisse

Adversarial testing

Prompt design

Analytical reasoning

Written communication

Ausbildung

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

Tools

Prompt engineering

Adversarial evaluation methodologies

Jobbeschreibung

Mercor seeks 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 AI behavior across high-risk, ambiguous topics.

Responsibilities include stress-testing models, identifying jailbreaks and policy failures, and documenting vulnerabilities for safety benchmarking. Collaboration with AI researchers will drive improvements in alignment and safety.