Role OverviewAs an AI Safety Specialist, you will be responsible for red teaming conversational AI models and agents, generating high-quality human data, and documenting reproducibly. You will work independently and asynchronously, and participate in optional higher-sensitivity projects with clear guidelines and wellness resources.
What You Will Do
Your main day-to-day responsibilities will include conversational AI model testing, human data generation, and documentation of results. You will also be responsible for explaining risks to technical and non-technical stakeholders.
Why It Might Be a Fit
We are looking for candidates with strong communication skills, prior red teaming experience in AI adversarial work, and fluency in English and Portuguese. Experience in Adversarial ML, cybersecurity, and socio-technical risk expertise are also desirable.
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 to technical and non-technical stakeholders
]]>