Role OverviewAs an AI Safety Specialist, you will work independently and asynchronously to identify and mitigate risks in conversational AI models. You will be responsible for red teaming, generating high-quality human data, and documenting reproducibly. You will work with customers to explain risks clearly and improve AI model performance.
What You Will Do
Your main responsibilities will be to red team conversational AI models, generate human data, apply structure, and document reproducibly. You will also work independently and asynchronously to meet deadlines.
Why It Might Be a Fit
We are looking for someone with native fluency in English and Finnish, prior red teaming experience, and strong communication skills. You should be able to thrive in a fast-paced environment and have experience in Adversarial ML, Cybersecurity, and socio-technical risk.
Requirements
- Native fluency in English and Finnish
- 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
- Ability to thrive on moving across projects and customers
]]>