AI Security Engineer

Amazon.com Services LLC is looking for an AI Security Engineer based in Arlington, VA to work closely with software development teams on securing AI applications. The role focuses on translating security expertise into practical threat modeling, code review, automation, and technical guidance, with responsibilities that span from investigations to internal training and outreach. TS/SCI with Polygraph eligibility is required for this position.

You’ll help strengthen AI and software systems by assessing threats, improving secure engineering practices, and building security automation that supports teams throughout the AI/ML lifecycle. The work includes both hands-on technical problem solving and collaboration to influence process and priorities for better security outcomes.

Key responsibilities

• Create, update, and maintain threat models across a wide variety of software projects.
• Conduct manual and automated code reviews, primarily in Java, Python, and JavaScript.
• Develop AI security automation tools.
• Deliver AI security training and outreach for internal development teams.
• Provide AI security architecture and design guidance.
• Solve AI security problems that require novel methods or approaches.
• Influence your team’s and partners’ process, priorities, and choices to improve outcomes.

Requirements

• Bachelor’s degree in Computer Science, Computer Systems Engineering, Software Development, Mathematics, or a similar STEM field.
• 3+ years of any combination of: threat modeling, secure coding, identity management and authentication, software development, cryptography, system administration, and network security.
• Programming experience in Python, Ruby, Go, Swift, Java, .Net, C++, or similar object-oriented languages.
• Knowledge of machine learning concepts and the ML model lifecycle, including training, deployment, and inference, plus AI/ML-specific threats such as adversarial inputs, model evasion, data poisoning, and model extraction.
• Current, active US Government Security Clearance of TS/SCI with Polygraph.

Technologies

• Java, Python, JavaScript
• Ruby, Go, Swift
• .Net, C++

Preferred qualifications

• Fundamentals of networking, security, databases (relational or NoSQL), and operating systems (Unix, Linux, and/or Windows).
• Hands-on experience securing or attacking AI/ML systems, including adversarial ML, red-teaming models, or ML threat detection (for example, familiarity with MITRE ATLAS).
• Security certifications such as GCIH, GSEC, GCFA, GREM, Security+, CISSP, CISA, or CISM.
• Experience configuring security automation (static/dynamic analysis, code-quality, container scanning) and integrating AI/ML security tooling into pipelines.

Compensation and location

• Location: Arlington, VA (onsite)
• Base salary: USD 159,300 - 202,400 per year

A day in the life

• Start by reviewing model telemetry and anomalies identified by overnight detection tooling, then triage findings and open an investigation into adversarial input patterns against a deployed model.
• Pull forensic data to determine what happened, drive containment, and capture lessons learned as a new detection.
• Later, review a scanning rule and integrate an AI/ML security automation tool into the pipeline.
• In the afternoon, document after-action findings and coordinate reporting across the team.

Benefits

• Health insurance (medical, dental, vision, prescription), Basic Life & AD&D, and option for Supplemental life plans
• EAP
• Mental Health Support
• Medical Advice Line
• Flexible Spending Accounts
• Adoption and Surrogacy Reimbursement coverage
• 401(k) matching
• Paid time off
• Parental leave
• Sign-on payments and Restricted Stock Units (RSUs)

Minimum qualifications

• Experience: 3 years minimum
• Education: Bachelor’s degree in Computer Science or similar STEM field