Frontier AI Safety Red Teamer

Mercor; Wien; Remote; EUR 70.000 - 110.000; Vollzeit

Zusammenfassung

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

Responsibilities include designing adversarial prompts, spotting jailbreaks and policy failures, evaluating model robustness across sensitive domains, and documenting vulnerabilities for benchmarking.

Qualifikationen

• Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or a related discipline.
• 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a 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

AI safety experience

Red Teaming

Ausbildung

Bachelor's degree or higher

Jobbeschreibung

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

Responsibilities include designing adversarial prompts, spotting jailbreaks and policy failures, evaluating model robustness across sensitive domains, and documenting vulnerabilities for benchmarking.