Frontier AI Risk Evaluations Scientist

United States Digital Space LLC; San Francisco, New York (CA, NY); On-site; USD 216,000 - 270,000; Full time

Benefits offered by this job

Health, dental and vision coverage

Retirement benefits

Learning and development stipend

Generous PTO

Commuter stipend

Job summary

Scale Labs seeks a Research Scientist focused on Frontier Risk Evaluations to design evaluation measures, harnesses and datasets that measure risk in frontier AI systems. You will build evaluation harnesses, work with government agencies to design risk mitigation studies, and publish methodologies for policymakers.

The ideal candidate has 3+ years addressing complex ML problems, a track record in generative AI research, and strong written and verbal communication skills for cross‑functional

Qualifications

• Commitment to our mission of promoting safe, secure, and trustworthy AI deployments in frontier contexts.
• Hands-on experience conducting technical research collaboratively; building and instrumenting ML pipelines; turning ideas into prototypes.
• Track record of published ML research, particularly in generative AI.
• At least three years of experience addressing sophisticated ML problems in research or product development.
• Strong written and verbal communication skills for cross-functional teams.

Responsibilities

• Design and create evaluation measures, harnesses and datasets to assess risks posed by frontier AI systems.
• Design harnesses to test AI models for dangerous capabilities and system vulnerabilities.
• Collaborate with government agencies or labs to scope and design evaluations to mitigate risks.
• Publish evaluation methodologies and write technical reports for policymakers.

Skills

Generative AI

ML research

Cross-functional collaboration

Written and verbal communication

Adversarial testing

Risk assessment

Tools

ML pipelines

Evaluation harnesses

Job description

Scale Labs seeks a Research Scientist focused on Frontier Risk Evaluations to design evaluation measures, harnesses and datasets that measure risk in frontier AI systems. You will build evaluation harnesses, work with government agencies to design risk mitigation studies, and publish methodologies for policymakers.

The ideal candidate has 3+ years addressing complex ML problems, a track record in generative AI research, and strong written and verbal communication skills for cross‑functional