jobs

Applied Scientist III, AI & AGI Security

We are seeking an Applied Scientist to contribute to the research and development of novel security validation and monitoring techniques for AI systems at scale. You will own and contribute to four critical work-streams:1. Real-Time Agent M

Company

Amazon

Location

New York, New York, USA

Status

Closed

Posted

2026-09-29T00:00:00+00:00

Amazon Security is hiring an applied scientist to research and build security validation and monitoring for AI systems. The work spans real-time monitoring of AI agents for anomalous actions and prompt injection; protection and automated remediation; security testing of AI applications and capabilities such as tool-use authorization and guardrail bypass; and discovering and cataloguing AI assets across the company. The posting asks for a PhD or a master's with six years of applied research, five years building machine-learning models, and Java, C++, or Python.