Frontier AI Risk Evaluations Scientist

JRNLClub; New York (NY); On-site; USD 216,000 - 270,000; Full time

Benefits offered by this job

Health, dental, vision coverage

Equity compensation

Job summary

Scale Labs seeks a Research Scientist focused on Frontier Risk Evaluations to design evaluation measures and harnesses for frontier AI systems. You will build datasets, test AI models, and collaborate with government agencies to scope and design risk evaluations.

Ideal candidates have 3+ years in ML research, a track record of publications in ML (preferably generative AI), and strong cross-functional communication skills. The role emphasizes safety-focused research and policy-relevant output.

Qualifications

• At least three years of experience addressing sophisticated ML problems.
• Experience building ML pipelines and evaluation harnesses.
• Published research in machine learning, especially generative AI.
• Strong written and verbal communication in cross-functional teams.

Responsibilities

• Design and build evaluation measures, harnesses and datasets for measuring frontier AI risks.
• Create evaluation harnesses to test AI models and systems.
• Collaborate with government agencies or labs to scope and design evaluations.
• Publish evaluation methodologies and technical reports for policymakers.

Skills

ML research

Policy research

Publications

Team collaboration

Tools

ML pipelines

Evaluation harnesses

Job description

Scale Labs seeks a Research Scientist focused on Frontier Risk Evaluations to design evaluation measures and harnesses for frontier AI systems. You will build datasets, test AI models, and collaborate with government agencies to scope and design risk evaluations.

Ideal candidates have 3+ years in ML research, a track record of publications in ML (preferably generative AI), and strong cross-functional communication skills. The role emphasizes safety-focused research and policy-relevant output.