AI Safety Red Team Expert (Remote)

name; Österreich; Vor Ort; EUR 84.000 - 100.000; Vollzeit

Zusammenfassung

Mercor connects elite creative and technical talent with leading AI research labs. This AI Safety Red Teamer role is remote under a contract arrangement. You will design adversarial prompts, identify jailbreaks and unsafe behaviors, and evaluate model robustness across diverse domains.

Collaborate with AI researchers to document vulnerabilities, contribute to safety benchmarking, and improve alignment and safety practices.

Qualifikationen

• Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy or related field.
• 5+ years of professional experience in AI Safety, AI Red Teeming, Trust & Safety, cybersecurity, 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 behaviors, 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

5+ years AI Safety experience

Analytical reasoning

Prompt design

Written communication

RLHF familiarity

SFT familiarity

AI Alignment understanding

Adversarial evaluation

Ausbildung

Bachelor's degree or higher in Computer Science or related

Jobbeschreibung

Mercor connects elite creative and technical talent with leading AI research labs. This AI Safety Red Teamer role is remote under a contract arrangement. You will design adversarial prompts, identify jailbreaks and unsafe behaviors, and evaluate model robustness across diverse domains.

Collaborate with AI researchers to document vulnerabilities, contribute to safety benchmarking, and improve alignment and safety practices.