Role OverviewWe are seeking an AI Safety Specialist to join our team at Mercor. As a red teamer, you will be responsible for conversational AI models and agents by performing jailbreaks, prompt injections, and bias exploitation. You will also generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks. You will work independently and asynchronously to meet deadlines while improving AI model performance.
What You Will Do
Your day-to-day responsibilities will include red teaming conversational AI models and agents, generating high-quality human data, applying structure to maintain consistent testing, and documenting reproducibly.
Why It Might Be a Fit
To be successful in this role, you will need to be able to explain risks clearly to technical and non-technical stakeholders, have prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing), and have a strong background in cybersecurity and socio-technical risk.
Requirements
- Fluent in English and Dutch
- Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing)
- Ability to explain risks clearly to technical and non-technical stakeholders
Benefits
- Competitive hourly rate of $48-$62/hour
]]>