AI Security Scientist — Real-Time Monitoring & Protection

Amazon Inc.; Seattle (WA); On-site; USD 143,000 - 193,000; Full time

Job summary

Amazon Security is seeking an Applied Scientist to advance security validation and monitoring of AI systems at scale. You will own four work streams: Real-Time Agent Monitoring, Protection & Automated Remediation, AI Application Validation, and AI Asset Discovery.

You will design and implement approaches for continuous behavioral analysis of AI agents in production. You will publish results at peer‑reviewed venues when appropriate, articulate challenges of current AI security threats, and

Qualifications

• 3+ years building models for business applications.
• Experience in patents or publications at top-tier peer-reviewed conferences or journals
• Experience programming in Java, C++, Python or related language
• Experience in algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing

Responsibilities

• Invent new research challenges at the product level.
• Contribute to the team's scientific agenda for AI security research.
• Publish results at peer-reviewed venues when appropriate.
• Articulate scientific challenges of AI security threats and address them.
• Design, implementation, and delivery of scientifically complex security solutions into production.
• Write significant portions of critical-path code for detection models, validation engines, protection technologies, and asset discovery/classification systems.
• Assess and select technologies for production systems.
• Provide peer reviews of code and architecture artifacts.

Skills

Java

C++

Python

Education

PhD or Master’s degree + 4+ years CS/CE/ML

Tools

Unix/Linux

Job description

Amazon Security is seeking an Applied Scientist to advance security validation and monitoring of AI systems at scale. You will own four work streams: Real-Time Agent Monitoring, Protection & Automated Remediation, AI Application Validation, and AI Asset Discovery.

You will design and implement approaches for continuous behavioral analysis of AI agents in production. You will publish results at peer‑reviewed venues when appropriate, articulate challenges of current AI security threats, and