Research Scientist, Agent Robustness

Scale AI
San Francisco, New York
Workplace: OnsiteFull timeUSD 197,400 - 246,750 annuallyFunction: Data Science & Machine LearningExperience: 3+ yearsSkills: ["Communication","Collaboration","Problem-solving"]

Scale’s Research Scientist for Agent Robustness works on safety and alignment of AI agents, developing harnesses to test agent behavior, exploring failure modes, and designing mitigations for systems with multiple interacting agents. The role collaborates across industry, government, and academia, publishing findings and turning research into prototypes, with a focus on RL techniques and post-training methods to advance safe AI deployments.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Scale AI
Scale AI
4 months ago

Research Scientist, Agent Robustness

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 17 hours agoStatus: Live

Job Summary

Scale’s Research Scientist for Agent Robustness works on safety and alignment of AI agents, developing harnesses to test agent behavior, exploring failure modes, and designing mitigations for systems with multiple interacting agents. The role collaborates across industry, government, and academia, publishing findings and turning research into prototypes, with a focus on RL techniques and post-training methods to advance safe AI deployments.
Location: San Francisco, New York
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Research the science of AI agent capabilities with a focus on safety, risk factors, and benchmarking methodologies.
  • •Design and build harnesses to test AI agents’ tendency to take harmful actions when pressured or tricked by environment factors.
  • •Design and build exploits and mitigations for failure modes as AI agents gain capabilities such as coding, web browsing, and general computer use.
  • •Characterize and design mitigations for potential failure modes or broader risks involving multiple interacting AI agents.
  • •Collaborate with cross-functional teams and publish findings to advance safe, trustworthy AI deployments.

Pay and Benefits

Salary: USD 197,400 - 246,750 annually
Equity and Bonus:Equity
Perks:Health InsuranceDentalVisionRetirement BenefitsLearning StipendCommuter BenefitsPaid Leave

Key Requirements

  • •3+ years of experience addressing sophisticated ML problems in research or product development.
  • •Experience with post-training and RL techniques such as RLHF, DPO, GRPO, and similar approaches.
  • •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.
  • •Ability to design evaluation harnesses and prototype ideas from research into working systems.
Experience:3+ yearsAI safetyMachine learningGenerative AI
Skills:CommunicationCollaborationProblem-solving
Languages:English
Tech Stack:RLHFDPOGRPOMachine learningGenerative 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