Senior AI Security Scientist - Real-Time Monitoring & AGI

Amazon Inc.; New York (NY); On-site; USD 184,000 - 249,000; Full time

Job summary

Amazon seeks a Senior Applied Scientist to lead security validation and monitoring research for AI systems at scale. You will own four workstreams: real-time agent monitoring, MCP server validation, AI-enabled application validation, and AI asset discovery across the company.

You will design production‑level security solutions, write critical code for detection and validation systems, and mentor other scientists while shaping cross-team security initiatives.

Qualifications

• PhD, or Master’s degree and 5+ years of applied research experience.
• Experience programming in Java, C++, Python or related language.
• 5+ years of building machine learning models for business applications.
• Experience with neural deep learning methods and machine learning.

Responsibilities

• Invent new research challenges in AI security and frame them for production-level impact.
• Drive scientific agenda for agent monitoring, validation research, and AI asset discovery; secure leadership buy-in.
• Publish research results at internal and external venues when appropriate.
• Articulate scientific challenges of AI security threats and present interventions.
• Make trade-offs between short-term security needs and long-term research investments.

Skills

Applied research

ML model development

Programming: Java

Programming: C++

Programming: Python

Neural networks

Education

PhD or Master’s with 5+ years experience

Tools

R

scikit-learn

Spark MLLib

MxNet

TensorFlow

NumPy

SciPy

Job description

Amazon seeks a Senior Applied Scientist to lead security validation and monitoring research for AI systems at scale. You will own four workstreams: real-time agent monitoring, MCP server validation, AI-enabled application validation, and AI asset discovery across the company.

You will design production‑level security solutions, write critical code for detection and validation systems, and mentor other scientists while shaping cross-team security initiatives.