About the job
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.
Responsibilities
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.
Qualifications
Minimum
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. You should be 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.
A 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.
Preferred
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.