← All roles

Research Scientist, Agent Robustness

Scale AI· Research
Apply on company site
Hybrid (San Francisco, CA; New York, NY)$216k - $270kfull-timePosted 7mo ago

About the role

Research Scientist focusing on agent robustness, AI safety, and risk evaluations to test and mitigate AI system failures, with a multi-sector collaboration approach and regular dissemination of findings.

Responsibilities

  • - Research the science of AI agent capabilities with a focus on safety and benchmarking methodologies
  • - Design and build harnesses to test AI agents’ tendency to take harmful actions under pressure or environmental manipulation
  • - Design and build exploits and mitigations for new failure modes as agents gain capabilities like coding, web browsing, and computer use
  • - Characterize and design mitigations for potential failure modes in systems with multiple interacting AI agents

Qualifications

  • - Commitment to safe, secure, and trustworthy AI deployments
  • - Experience conducting technical research collaboratively with agent scaffolding and evaluation harnesses
  • - Experience with post-training and RL techniques (e.g., RLHF, DPO, GRPO)
  • - Track record of published ML research, especially in generative AI
  • - At least three years addressing sophisticated ML problems in research or product development
  • - Strong written and verbal communication skills for cross-functional work

Skills

Required:Agent robustness researchEvaluation harness designRL techniques (RLHF, DPO, GRPO)Machine learning researchTechnical communication

Benefits

  • comprehensive health, dental and vision coverage
  • retirement benefits
  • learning and development stipend
  • generous PTO
  • potential commuter stipend
Last updated Jul 8, 2026. Interested? Apply on the company site.
Scale AI logo

About Scale AI

Data-centric infrastructure to accelerate the development of AI

Scale accelerates the development of AI within organizations of any size to deliver critical business insights and operational efficiency. Its data-centric infrastructure platform leverages RLHF (Reinforced Learning with Human Feedback) to help organizations build the strongest AI models that supercharge their business, with customers across industries including Meta, Microsoft, U.S. Army, DoD’s Defense Innovation Unit, Open AI, General Motors, Toyota Research Institute, Brex, Instacart and Flexport.

artificial-intelligenceliquid-ai-recruiting-targetmachine-learning
Company profileWebsite

More open roles at Scale AI