Research Scientist, Applied Machine Learning Security (Agent Systems)

What you'll do

• Conduct original security research on deployed agentic ML systems interacting with tools, APIs, and sensitive data.
• Identify and characterize vulnerabilities such as indirect prompt injection, tool misuse, and privilege escalation.
• Build and maintain adversarial testing frameworks that reflect real attacker incentives and multi-step attack patterns.
• Develop security mitigations that meet production requirements for latency, reliability, debuggability, and privacy.
• Define trust boundaries and threat models for agentic ML across platforms to create actionable security requirements.
• Translate research insights into architectural decisions, design guidance, and launch requirements for product engineering teams.
• Set standards for applied ML security research and mentor other researchers within the organization.

What we're looking for

• Ph.D. or equivalent experience in machine learning, security, systems, or a related field.
• Demonstrated experience in applied ML security, adversarial ML, or systems security with real-world impact.
• Strong experimental and engineering skills with an emphasis on reproducibility and operational relevance.
• Experience researching or securing LLM-based or tool-augmented ML systems (preferred).
• Ability to work fluidly across research, engineering, and security review processes (preferred).
• Track record of influencing production systems through research-driven insights (preferred).
• Publications in top venues are a plus (preferred).