Research Scientist, Applied Machine Learning Security (Agent Systems), SEAR
Core
Lead applied security research on production agentic ML systems to identify vulnerabilities and drive defenses into shipping products.
Role type
Senior IC applied machine learning security researcher (agent systems)
Builds
Secure agentic ML systems for Apple Intelligence
Domain
Machine Learning Security / Agentic Systems
Deliverable
production ML models
Required skills
applied ML security, adversarial ML, systems security, experimental design, threat modeling, architectural design, technical leadership, cross-functional collaboration, vulnerability characterization, defense development
Preferred skills
LLM security, tool-augmented ML research, production impact via research, publications in top venues
Technologies
agentic ML frameworks, adversarial testing frameworks, ML platforms
Responsibilities
Conduct original security research on deployed agentic ML systems interacting with tools and APIs; Design realistic adversarial evaluations reflecting real attacker incentives; Develop mitigations compatible with production latency and privacy constraints; Define trust boundaries and threat models for agent deployments; Partner with ML platform and product teams to translate research into design guidance; Set standards for applied ML security research and mentor other researchers
Seniority
Senior, hands-on IC with research leadership