About the job
As a Research Scientist focused on Frontier Risk Evaluations, you will design and create evaluation measures, harnesses and datasets for measuring the risks posed by frontier AI systems. This includes designing and building harnesses to test AI models and systems, working with government agencies or other labs to collectively scope and design evaluations, and publishing evaluation methodologies and technical reports for policymakers.
Responsibilities
- Design and build harnesses to test AI models and systems (including agents) for dangerous capabilities such as security vulnerability exploitation, CBRN uplift, and other high-risk activities
- Work with government agencies or other labs to collectively scope and design evaluations to measure and mitigate risks posed by advanced AI systems
- Publish evaluation methodologies and write technical reports for policymakers
Qualifications
Minimum
- Commitment to our mission of promoting safe, secure, and trustworthy AI deployments in the industry as frontier AI capabilities continue to advance
- Practical experience conducting technical research collaboratively
- A track record of published research in machine learning, particularly in generative AI
- At least three years of experience addressing sophisticated ML problems, whether in a research setting or in product development
- Strong written and verbal communication skills to operate in a cross-functional team
Preferred
- Experience in crafting evaluations and benchmarks, or a background in data science roles related to LLM technologies
- Experience with red-teaming or adversarial testing of AI systems
- Familiarity with AI safety policy frameworks (e.g., NIST AI RMF, EU AI Act, Korea AI Basic Act)