Applied Scientist - Satellite Security ML (Production)

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

Job summary

Amazon.com Services LLC in Arlington, VA is seeking an Applied Scientist to join the Leo Space Security R&D team defending the constellation infrastructure. You will build statistical and behavioral models on security telemetry, design privacy-preserving representations, and ship production-grade detections that scale across global ground stations and factories.

You will collaborate with security engineers and scientists, publish technical artifacts, and contribute to state-of-the-art

Qualifications

• PhD or MS with 4+ years in CS/ML or related field
• Experience building models for business/security applications
• Fluency in Python; systems language like Rust or C++ is a plus
• Experience with statistical modeling on large, heterogeneous datasets
• Experience with popular DL frameworks (PyTorch, TensorFlow)

Responsibilities

• Build behavioral and statistical models for security telemetry to baseline normal activity.
• Design privacy-preserving representations of sensitive data while maintaining detection performance.
• Define methodologies for difficult, loosely defined problems with cross-domain data.
• Develop metrics/evaluation frameworks to measure model and detection performance.
• Contribute to neurosymbolic reasoning platforms and production-grade components.

Skills

Statistical modeling

Python

Deep learning frameworks

Time-series analysis

Anomaly detection

Data storytelling

Education

PhD in CS/CE/ML

MS in CS/CE/ML

Tools

C++

Rust

Job description

Amazon.com Services LLC in Arlington, VA is seeking an Applied Scientist to join the Leo Space Security R&D team defending the constellation infrastructure. You will build statistical and behavioral models on security telemetry, design privacy-preserving representations, and ship production-grade detections that scale across global ground stations and factories.

You will collaborate with security engineers and scientists, publish technical artifacts, and contribute to state-of-the-art