AI Safety Expert - Red Team

Mercor
New York, NY
Job Description
Role Overview

Mercor connects elite creative and technical talent with leading AI research labs. The AI Safety Expert - Red Team will work independently and asynchronously to identify jailbreaks, prompt injections, and misuse cases in conversational AI models and agents.

What You Will Do

The role responsibilities include generating high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks, as well as documenting reproducibly by producing reports, datasets, and attack cases.

Why It Might Be a Fit

The ideal candidate will have prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing, and the ability to explain risks clearly to technical and non-technical stakeholders.

Requirements

  • Fluent in English & Punjabi with native fluency
  • Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
  • Ability to explain risks clearly to technical and non-technical stakeholders
]]>