As an AI Security Engineer, you will work with software development teams to ensure the security of AI applications. You will review code for security issues, build frameworks to help developers create more secure software, and adjust designs to improve protection. You will also perform security research, analyze bug reports, conduct risk assessments, develop automation, maintain documentation, and create tools that reduce security risks. Your work drives secure, reliable AI applications for Amazon's customers.
This position requires that the candidate selected be a US Citizen and must currently possess and maintain an active TS/SCI security clearance with polygraph.
Key job responsibilities
- You will create, update, and maintain threat models for a wide variety of software projects.
- You will perform manual and automated code review, primarily in Java, Python, and JavaScript
- You will develop AI security automation tools.
- You will perform AI security training and outreach for internal development teams.
- You will provide AI security architecture and design guidance.
- You will independently solve AI security problems that require novel methods or approaches.
- You will influence your team's and partners' process, priorities, and choices to improve outcomes.
A day in the life
Your day starts with a sweep of model telemetry: you review anomalies the detection tooling surfaced overnight, triage them, and open an investigation into an adversarial input pattern against a deployed model. You pull forensic data to establish what happened, drive the incident through containment, and capture the learning as a new detection. Midday, you review a scanning rule and integrate an AI/ML security automation tool into the pipeline. In the afternoon, you document after-action findings and coordinate reporting among the team.
BASIC QUALIFICATIONS
- Bachelor's degree in Computer Science, Computer Systems Engineering, Software Development, Mathematics, or a similar STEM (Science, Technology, Engineering, and Mathematics) field
- 3+ years of any combination of the following: threat modeling experience, secure coding, identity management and authentication, software development, cryptography, system administration and network security experience
- Experience programming in Python, Ruby, Go, Swift, Java, .Net, C++ or similar object oriented language
- Knowledge of machine learning concepts and the ML model lifecycle (training, deployment, inference), and of AI/ML-specific threats such as adversarial inputs, model evasion, data poisoning, or model extraction.
- Current, active US Government Security Clearance of TS/SCI with Polygraph.
PREFERRED QUALIFICATIONS
- Knowledge of fundamentals of networking, security, databases (relational or NoSQL), operating systems (Unix, Linux, and/or Windows)
- Hands-on experience securing or attacking AI/ML systems (adversarial ML, red-teaming models, or ML threat detection), such as familiarity with MITRE ATLAS.
- Security certification 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.
The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance 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, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits.
USA, VA, Herndon - 159,300.00 - 202,400.00 USD annually
