Role OverviewAI Safety Expert - Red Team will perform jailbreaks, prompt injections, misuse cases, and bias exploitation to ensure AI model safety. The role involves annotating failures, classifying vulnerabilities, and flagging systemic risks. The expert will work independently and asynchronously to improve AI model performance.
What You Will Do
The main responsibilities include red teaming conversational AI models and agents, generating high-quality human data, applying structure, and documenting reproducibly. The expert will also work to improve AI model performance and ensure safety.
Why It Might Be a Fit
To be a fit for this role, you should have native fluency in English and Portuguese, 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
- Native fluency in English and Portuguese (global, excluding Brazilian Portuguese)
- Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
- Strong communication skills to explain risks clearly to technical and non-technical stakeholders
Benefits
- Hourly compensation: $29–$45
]]>