AI Safety Specialist

Mercor
New York, NY
Job Description
Role Overview

We are seeking an AI Safety Specialist to join our team. As a red team conversational AI models and agents, you will identify jailbreaks, prompt injections, and misuse cases. You will also generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.

What You Will Do

Your day-to-day responsibilities will include red teaming, generating human data, applying structure, and documenting reproducibly to produce reports, datasets, and attack cases.

Why It Might Be a Fit

You will thrive in this role if you have prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing, and strong communication skills to explain risks clearly to technical and non-technical stakeholders.

Requirements

  • Fluent in English & Danish
  • Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
  • Strong communication skills
  • Ability to thrive on moving across projects and customers

Benefits

  • Hourly compensation up to $62
  • Flexible remote work arrangement
]]>