Research Scientist, Frontier Risk Evaluations
$216k - $270k • San Francisco, CA; New York, NY
Posted 2mo ago
Job Location
San Francisco, CA; New York, NY
Tech Stack
Remote Work Policy
On-site
Categories
AI Research Engineer
About the job
Scale Labs is seeking a Research Scientist focused on Frontier Risk Evaluations to join a new team dedicated to policy research. This role bridges the gap between AI research and global policymakers, aiming to inform scientific decisions about AI risks and capabilities. The team tackles complex problems in agent robustness, AI control protocols, and AI risk evaluations to help governments, industry, and the public understand and mitigate AI risks while promoting AI adoption. This position involves designing and creating evaluation measures, harnesses, and datasets for assessing the risks posed by frontier AI systems, with opportunities to collaborate broadly and publish findings.
Responsibilities
- Design and build harnesses to test AI models and systems for dangerous capabilities.
- Collaborate with government agencies or other labs to design evaluations for advanced AI systems.
- Publish evaluation methodologies and write technical reports for policymakers.
Requirements
- Commitment to promoting safe, secure, and trustworthy AI deployments.
- Practical experience conducting collaborative technical research.
- Experience building and instrumenting ML pipelines.
- Experience writing evaluation harnesses.
- Ability to quickly prototype new ideas from research literature.
- Track record of published research in machine learning, particularly generative AI.
- At least three years of experience addressing sophisticated ML problems.
- Strong written and verbal communication skills for cross-functional teams.
Benefits
- Base salary
- Equity
- Comprehensive health, dental and vision coverage
- Retirement benefits
- Learning and development stipend
- Generous PTO
- Commuter stipend