Role OverviewAI Safety Experts — English & Dutch will work on red teaming conversational AI models and agents, generating high-quality human data, and documenting reproducibly to produce reports and datasets. The role requires working independently and asynchronously to meet deadlines while improving AI model performance.
What You Will Do
Red team conversational AI models and agents, generate high-quality human data, apply structure to ensure consistent testing, document reproducibly, and work independently and asynchronously.
Why It Might Be a Fit
The ideal candidate has prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing, and can explain risks clearly to technical and non-technical stakeholders.
Requirements
- Fluent in English & Dutch
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
- Ability to explain risks clearly to technical and non-technical stakeholders
]]>