Research Scientist, Safety Post Training

Scale AI
San Francisco, New York
Workplace: OnsiteFull timeUSD 216,000 - 270,000 annuallyFunction: Data Science & Machine LearningExperience: 3+ yearsSkills: ["Communication","Collaboration","Writing","Research","Critical thinking"]

Research Scientist focused on post-training methods and interpretability to improve safety, robustness, and alignment of frontier AI systems. Collaborates with policymakers, engineers, and researchers to translate post-training findings into actionable safety standards, evaluation benchmarks, and best practices while contributing to policy-relevant research and publications.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Scale AI
Scale AI
3 months ago

Research Scientist, Safety Post Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 22 hours agoStatus: Live

Job Summary

Research Scientist focused on post-training methods and interpretability to improve safety, robustness, and alignment of frontier AI systems. Collaborates with policymakers, engineers, and researchers to translate post-training findings into actionable safety standards, evaluation benchmarks, and best practices while contributing to policy-relevant research and publications.
Location: San Francisco, New York
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Design and run post-training pipelines to study how training choices affect model safety, robustness, and alignment properties.
  • •Develop interpretability-informed evaluations that reveal how and why models produce unsafe, deceptive, or otherwise undesirable behaviors, and use those insights to guide targeted mitigations.
  • •Collaborate with policymakers, engineers, and other researchers to translate post-training and interpretability findings into actionable safety standards, evaluation benchmarks, and best practices.

Pay and Benefits

Salary: USD 216,000 - 270,000 annually
Perks:Health InsuranceDentalVisionRetirement BenefitsLearning BudgetCommuter BenefitsPaid Leave

Key Requirements

  • •At least three years of experience addressing sophisticated ML problems, whether in a research setting or in product development.
  • •Experience with post-training and RL techniques such as RLHF, DPO, GRPO, and similar approaches.
  • •A track record of published research in machine learning, particularly in generative AI.
  • •Strong written and verbal communication skills to operate in a cross-functional team.
  • •Commitment to the mission of promoting safe, secure, and trustworthy AI deployments in the industry as frontier AI capabilities continue to advance.
Experience:3+ yearsMachine learningGenerative AIPolicy research
Skills:CommunicationCollaborationWritingResearchCritical thinking
Languages:English
Tech Stack:RLHFPost-trainingInterpretabilityGenerative AI

Company Brief

Scale AI
Provides data labeling, annotation, and infrastructure services to accelerate machine learning and AI development. Supplies high-quality training data, tooling, and APIs for customers in autonomous vehicles, mapping, robotics, and enterprise AI applications.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series E+
Headquarters: San Francisco, United States
Founded: 2016
WebsiteLinkedIn