AI Safety Expert - Red Team

Mercor
San Francisco, CA
Job Description
Role Overview

Mercor connects elite creative and technical talent with leading AI research labs. The AI Safety Expert - Red Team will work on conversational AI models and agents, generating high-quality human data, and documenting reproducibly.

What You Will Do

Conversational AI models and agents, generate high-quality human data, annotate failures, classify vulnerabilities, and flag systemic risks.

Why It Might Be a Fit

The ideal candidate will have strong communication skills, adaptability, and experience in AI adversarial work, cybersecurity, or socio-technical probing.

Requirements

  • Fluent Language Skills Required: English & Thai
  • Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
  • Strong communication skills. Explain risks clearly to technical and non-technical stakeholders
  • Adaptability. Thrive on moving across projects and customers

Benefits

  • Competitive hourly rate ($24–$35/hour)
  • Remote work arrangement
]]>