Research Scientist (Agent Robustness)

• As the leading data and evaluation partner for frontier AI companies, Scale plays an integral role in understanding the capabilities and safeguarding AI models and systems
• Building on this expertise, Scale Labs has launched a new team focused on policy research, to bridge the gap between AI research and global policymakers to make informed, scientific decisions about AI risks and capabilities
• Our research tackles the hardest problems in agent robustness, AI control protocols, and AI risk evaluations to help governments, industry, and the public understand and mitigate AI risk while maximizing AI adoption
• This team collaborates broadly across industry, the public sector, and academia and regularly publishes our findings. We are actively seeking talented researchers to join us in shaping this vision
• As a Research Scientist working on Agent Robustness you will work on the fundamental challenges of building AI agents that are safe and aligned with humans. For example, you might:
• Research the science of AI agent capabilities with a focus on how they relate to safety, risk factors, and methodologies for benchmarking them
• Design and build harnesses to test AI agents’ tendency to take harmful actions when pressured to do so by users or tricked into doing so by elements of their environment
• Design and build exploits and mitigations for new and unique failure modes that arise as AI agents gain affordances like coding, web browsing, and computer use
• Characterize and design mitigations for potential failure modes or broader risks of systems involving multiple interacting AI agents

Benefits

• Health & Wellbeing: Our holistic approach to supporting Scaliens includes comprehensive health coverage, dental and vision insurance, mental healthcare services, and more. PTO policies and accommodating schedules ensure you’ll get time off when you need it to relax and recharge. Note that our offerings may vary by region as we strive to respond to the unique needs of Scaliens around the globe.
• Personal & Career Growth: Continuously learn and grow through annual learning & development stipend, attending leadership breakfasts, manager training, speaker series, and joining an ERG.
• Building Scale Community: We welcome guests to our offices, and you can expect to see Scalien families and friends around. Join local happy hours, and accept invites to game nights, book clubs, and many other employee-led community events.
• Parental Support: Balancing work and family is essential, and Scale understands the importance of having adequate leave policies in place to promote a healthy home and work life.- At least three years of experience addressing sophisticated ML problems, whether in a research setting or in product development
• Commitment to our mission of promoting safe, secure, and trustworthy AI deployments in the industry as frontier AI capabilities continue to advance
• Experience with post-training and RL techniques such as RLHF, DPO, GRPO, and similar approaches
• Strong written and verbal communication skills to operate in a cross-functional team
• A track record of published research in machine learning, particularly in generative AI
• Practical experience conducting technical research collaboratively. You should be comfortable building and leveraging agent scaffolding, designing evaluation harnesses, and quickly turning new ideas from the research literature into working prototypes
• Hands-on experience with agent evaluation frameworks such as SWE-bench, WebArena, OSWorld, Inspect, or similar tools
• Experience with red-teaming, prompt injection, or adversarial testing of AI systems
• Our research interviews are crafted to assess candidates’ skills in practical ML prototyping and debugging, their grasp of research concepts, and their alignment with our organizational culture. We will not ask any LeetCode-style questions. If you’re excited about advancing AI safety and contributing to our mission, we encourage you to apply, even if your experience doesn’t perfectly align with every requirement