AI Safety Specialist - Remote | Upto $84/hr

Mercor is a premier platform connecting elite technical and creative talent with leading AI research labs. We are currently seeking an AI Safety Specialist to join our team in a fully remote capacity, focusing on the critical task of ensuring the safety and robustness of frontier AI models.

Key responsibilities

• Design and execute adversarial prompts to stress-test frontier AI models for potential vulnerabilities.
• Identify and document unsafe behaviors, jailbreaks, hallucinations, and policy failures within AI systems.
• Evaluate model robustness across sensitive domains such as misinformation, cyber security, biosecurity, and political content.
• Collaborate closely with AI researchers to contribute to safety benchmarking, red-teaming reports, and model alignment strategies.

Requirements

• Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Psychology, Biology, Public Policy, or a related discipline.
• Minimum of 5 years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, or related investigative fields.
• Strong analytical reasoning skills combined with advanced prompt design and clear written communication abilities.
• Proven experience in designing adversarial prompts or evaluating the performance of frontier AI systems.
• Expertise in specific grey-area domains such as biosecurity, scientific safety, or misinformation is highly valued.

What we offer

• The opportunity to work at the forefront of AI safety and alignment research.
• A fully remote work environment that supports global collaboration with top-tier AI research labs.
• Engagement in high-impact projects that directly influence the development and safety standards of next-generation AI technologies.