Remote AI Safety Red Teamer – Spain

FUT‑URE; País Vasco; A distancia; EUR 86.000 - 103.000; Jornada completa

Descripción de la vacante

Mercor is seeking an AI Safety Specialist for a remote engagement. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks, unsafe behaviors, and policy failures, and help quantify robustness across sensitive domains.

Collaborate with AI researchers to improve model alignment, robustness, and safety, contributing to safety benchmarks and red-teaming reports. A strong background in AI safety and 5+ years of experience is required.

Formación

• Bachelor's degree in CS, cybersecurity, journalism, communications, psychology, biology, chemistry, public policy, or related field.
• 5+ years of professional experience in AI safety, AI red teaming, trust & safety, cybersecurity, investigative journalism, or related field.
• Strong analytical reasoning, prompt design, and written communication skills.
• Experience designing adversarial prompts or evaluating frontier AI systems.

Responsabilidades

• 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.

Conocimientos

Adversarial prompts design

AI Safety

Prompt engineering

Analytical reasoning

Written communication

Educación

Bachelor's degree or higher in CS / related

Descripción del empleo

Mercor is seeking an AI Safety Specialist for a remote engagement. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks, unsafe behaviors, and policy failures, and help quantify robustness across sensitive domains.

Collaborate with AI researchers to improve model alignment, robustness, and safety, contributing to safety benchmarks and red-teaming reports. A strong background in AI safety and 5+ years of experience is required.