About this role
Scale AI is seeking a Research Scientist to join their new policy research team focused on frontier AI risks. You will design and build evaluation measures, harnesses, and datasets to assess risks posed by advanced AI systems, collaborating with government agencies and publishing findings. This role is ideal for researchers with practical experience in ML pipelines, generative AI, and a commitment to safe AI deployments.
What we are looking for 6
- Design and build harnesses to test AI models for dangerous capabilities
- Collaborate with government agencies on AI risk evaluations
- Publish evaluation methodologies and technical reports for policymakers
- Practical experience building ML pipelines and evaluation harnesses
- Track record of published research in machine learning, particularly generative AI
- At least three years of experience addressing sophisticated ML problems