Research Scientist, AI Controls and Monitoring
About the role
Research Scientist focused on AI controls, monitoring, and alignment to ensure advanced AI models remain aligned with intended goals, even in high-stakes or adversarial environments. Role involves designing methods, systems, and experiments for real-time monitoring, layered control, red-team simulations, and collaboration with policymakers, engineers, and researchers.
Responsibilities
- Develop monitoring techniques and observability methods that track AI behavior in real time to identify and flag deviations, emergent capabilities, or anomalous outputs
- Research mechanisms for layered control, including fail-safes, oversight protocols, and intervention methods that can halt or redirect AI systems when risks are detected
- Design red-team simulations to probe weaknesses in oversight and control mechanisms, and build mitigations to close identified gaps
- Collaborate with policymakers, engineers, and other researchers to establish standards and benchmarks for AI monitoring and escalation
Qualifications
- Commitment to mission of promoting safe, secure, and trustworthy AI deployments in the industry as frontier AI capabilities continue to advance
- Practical experience conducting technical research collaboratively; comfortable designing control and monitoring experiments for AI systems, building prototype systems, and turning ideas into working prototypes
- Track record of published research in machine learning, particularly in generative AI
- At least three years of experience addressing sophisticated ML problems, whether in research or product development
- Strong written and verbal communication skills to operate in a cross-functional team
Skills
Benefits
- comprehensive health, dental and vision coverage
- retirement benefits
- learning and development stipend
- generous PTO
- commuter stipend (potential eligibility)
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.
More open roles at Scale AI
- Strategic Contracts Lead, Public Sector6d agoWashington, DC · Public Sector
- Web Designer, Brand Web Experience6d agoSan Francisco, CA · Marketing
- Head of Strategic Partnerships, Global Systems Integrators6d agoSan Francisco, CA · Enterprise Sales
- Safety Research Scholar - Human Frontier Labs6d agoHybrid (United States) · Human Frontier Collective
- Machine Learning Research Intern (Summer 2027)6d agoHybrid (San Francisco, CA), Hybrid (New York, NY) · University