Research Scientist, Agent Robustness

Scale Labs, 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.

• 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.

• Commitment to our 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 building and leveraging agent scaffolding, designing evaluation harnesses, and quickly turning new ideas from the research literature into working prototypes.
• 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.
• At least three years of experience addressing sophisticated ML problems, whether in a research setting or in product development.
• Strong written and verbal communication skills to operate in a cross‑functional team.

• Hands‑on experience with agent evaluation frameworks such as SWE‑bench, Web Arena, 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 Leet Code‑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.

Compensation packages at Scale for eligible roles include base salary, equity, and benefits. The range displayed on each job posting reflects the minimum and maximum target for new hire salaries for the position, determined by work location and additional factors, including job‑related skills, experience, interview performance, and relevant education or training. Scale employees in eligible roles are also granted equity‑based compensation, subject to Board of Director approval.

You’ll also receive benefits including, but not limited to:
Comprehensive health, dental and vision coverage, retirement benefits, a learning and development stipend, and generous PTO. Additionally, this role may be eligible for additional benefits such as a commuter stipend.

Base salary range for this full‑time position in the locations of San Francisco, New York, Seattle is: $197,400 - $246,750 USD.

Policy requires a 90‑day waiting period before reconsidering candidates for the same role.

At Scale, our mission is to develop reliable AI systems for the world’s most important decisions. Our products provide the high‑quality data and full‑stack technologies that power the world’s leading models, and help enterprises and governments build, deploy, and oversee…