Frontier AI Safety Red Team Specialist

Mercor; Brussel Hoofdstad; À distance; EUR 80 000 - 120 000; Plein temps

Résumé du poste

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 AI behavior across complex, high-risk topics.

Responsibilities include designing adversarial prompts, identifying jailbreaks and policy failures, and evaluating model robustness across sensitive domains.

Qualifications

• 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.

Responsabilités

• 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.

Connaissances

Adversarial testing

Prompt design

AI safety

Red teaming

Formation

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

Outils

Jailbreak testing tooling

Description du poste

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 AI behavior across complex, high-risk topics.

Responsibilities include designing adversarial prompts, identifying jailbreaks and policy failures, and evaluating model robustness across sensitive domains.