Applied Scientist: Real-Time AI Security & AGI

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

Benefits offered by this job

Health insurance

RSUs

401(k) matching

Paid time off

Job summary

Amazon is seeking an Applied Scientist III in AI & AGI Security to advance research and develop scalable security validation and monitoring for AI systems. You will own multiple workstreams including real-time agent monitoring, automated remediation, validation of AI capabilities, and asset discovery across the company.

The role involves framing new research challenges, publishing results, and delivering scientifically complex security solutions into production, with significant coding for

Qualifications

• 5+ years building ML models for business applications.
• PhD or Master’s degree with 6+ years of applied research.
• Experience programming in Java, C++, Python or related language.
• Experience with neural deep learning methods and ML.

Responsibilities

• Identify and frame new AI security research challenges requiring novel scientific approaches.
• Contribute to the team’s scientific agenda across monitoring, protection, remediation, validation, and asset discovery.
• Publish research results at peer‑reviewed internal and external venues when appropriate.
• Articulate scientific challenges of AI security threats and deliver novel research to address them.
• Design and deliver production-grade security solutions, including new systems or evolutions of existing ones.

Skills

Machine Learning

Java

C++

Python

Deep Learning

Research

Education

PhD or Master’s + 6+ years applied research

Tools

R

scikit-learn

Spark MLLib

MxNet

TensorFlow

NumPy

SciPy

Job description

Amazon is seeking an Applied Scientist III in AI & AGI Security to advance research and develop scalable security validation and monitoring for AI systems. You will own multiple workstreams including real-time agent monitoring, automated remediation, validation of AI capabilities, and asset discovery across the company.

The role involves framing new research challenges, publishing results, and delivering scientifically complex security solutions into production, with significant coding for