Overview In this role you design evaluation measures, harnesses, and datasets to quantify risks posed by frontier AI systems and help policymakers understand and mitigate these risks. You will build and instrument evaluation pipelines, collaborate with government agencies and labs, and publish methodologies to support safe, trustworthy AI deployments. This role sits at the intersection of research, tooling, and policy, offering impact across industry, government, and academia. You will work with cross-functional teams to translate cutting-edge research into practical risk evaluation tools and reports.
Compensation / Benefits- Comprehensive health, dental and vision coverage
- Retirement benefits
- Learning and development stipend
- Generous PTO
- Commuter stipend
- Equity-based compensation
Responsibilities- Design and build evaluation harnesses to test AI models and systems for dangerous capabilities
- Collaborate with government agencies or labs to scope and design evaluations for mitigating AI risks
- Publish evaluation methodologies and write technical reports for policymakers
- Create measures, harnesses, and datasets to quantify frontier AI risks
Key requirements- Commitment to safe, secure, and trustworthy AI deployments
- Practical experience conducting technical research in a collaborative setting
- Ability to build and instrument ML pipelines, write evaluation harnesses, and prototype ideas from research
- Track record of published ML research, especially in generative AI
- Minimum of three years addressing sophisticated ML problems in research or product development
- Strong written and verbal communication for cross-functional collaboration
- Cross-functional collaboration
- Strong written and verbal communication
- Ability to translate research ideas into working prototypes
- ML pipelines
- Evaluation harnesses
- Generative AI research
