Applied ML Security Scientist — Agent Systems

Apple Inc.; Cupertino, Northern (CA, KY); Hybrid; USD 185,000 - 278,000; Full time

Job summary

Apple Inc. in Cupertino seeks a Research Scientist in Applied ML Security for agent systems. You will lead applied security research on production ML systems, focusing on agentic and tool-using models deployed at scale, and translate findings into design changes and defensive measures.

Collaborate with ML platform, product security, and engineering teams to shape threat models, implement mitigations, and guide releases. Strong communication and publishing track desirable; PhD preferred.

Qualifications

• 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.

Responsibilities

• Lead applied research on production agent systems: identify vulnerabilities and design defenses for tool-using ML systems.
• Design realistic adversarial evaluations reflecting real attacker incentives and system complexity.
• Drive defenses into shipping systems with latency, reliability, and privacy constraints.
• Own threat models for agent deployments across Apple platforms and services.
• Bridge research and engineering to translate insights into design guidance, test infra, and release criteria.
• Provide technical leadership and set standards for ML security research across the organization.

Skills

Applied ML security

Adversarial ML

Systems security

Education

PhD or equivalent

Job description

Apple Inc. in Cupertino seeks a Research Scientist in Applied ML Security for agent systems. You will lead applied security research on production ML systems, focusing on agentic and tool-using models deployed at scale, and translate findings into design changes and defensive measures.

Collaborate with ML platform, product security, and engineering teams to shape threat models, implement mitigations, and guide releases. Strong communication and publishing track desirable; PhD preferred.