AI Safety Specialist

Mercor
San Francisco, CA
Job Description
Role Overview

As an AI Safety Specialist, you will be responsible for red teaming conversational AI models and agents, generating high-quality human data, and applying structure to maintain consistent testing. You will document reproducibly and produce reports, datasets, and attack cases for customer action.

What You Will Do

Your day-to-day responsibilities will include conversational AI model and agent red teaming, human data generation, and applying structure to maintain consistent testing.

Why It Might Be a Fit

To be a fit for this role, you must have prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing, and strong communication skills for technical and non-technical stakeholders.

Requirements

  • Fluent in English & Norwegian
  • Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
  • Structured approach using frameworks or benchmarks
  • Strong communication skills for technical and non-technical stakeholders
  • Adaptability to move across projects and customers
]]>