Applied Scientist – Satellite Security & AI Defense

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

Job summary

Amazon.com Services LLC - A57 is seeking an Applied Scientist to join the Leo Infrastructure and IP Security team, focusing on building statistical and behavioral models to defend global satellite-ground infrastructure. You will work with diverse telemetry and industrial data sources, shaping production-grade security detections and privacy-aware representations.

You will collaborate with senior scientists to design evaluation metrics, publish rigorous results, and contribute to deployment

Qualifications

• 3+ years of building models for business applications.
• PhD or Master’s degree and 4+ years of CS, CE, ML or related field experience.
• Experience with statistical modeling and analysis of large, heterogeneous datasets, including anomaly detection, time-series analysis, or behavioral baselining.
• Fluency in Python; experience with a systems language such as Rust or C++ is a plus.
• Experience with popular deep learning frameworks (e.g., PyTorch, TensorFlow).

Responsibilities

• Build behavioral and statistical models that baseline normal activity across heterogeneous security telemetry, including specialized industrial-control and factory-floor data sources, so detections extend to new environments with low false-positive rates.
• Design privacy-preserving representations of sensitive security data, and verify that models and detections tuned against them remain accurate against the real data — turning data-protection guarantees into measurable, provable properties rather than assertions.
• Define the methodology and own the analysis for difficult, loosely defined problems: gather complex data across domains, select the right techniques from a range of data science methods, and justify your approach with evidence.
• Develop the metrics and evaluation frameworks that measure model and detection performance against threat actor behavior before a model is trusted in production.
• Contribute to the team's neurosymbolic reasoning platform, adapting state-of-the-art techniques from the literature and shipping components at production quality.
• Document your work with the rigor of a peer-reviewed publication, and communicate results clearly to both scientific and security-operations audiences.

Skills

Python

Rust

C++

PyTorch

TensorFlow

Statistical modeling

Anomaly detection

Behavioral baselining

Time-series analysis

Education

PhD

Master's degree in CS/CE/ML

Tools

PyTorch

TensorFlow

Job description

Amazon.com Services LLC - A57 is seeking an Applied Scientist to join the Leo Infrastructure and IP Security team, focusing on building statistical and behavioral models to defend global satellite-ground infrastructure. You will work with diverse telemetry and industrial data sources, shaping production-grade security detections and privacy-aware representations.

You will collaborate with senior scientists to design evaluation metrics, publish rigorous results, and contribute to deployment