Applied Scientist, Security Analytics for Global Infrastructure

Amazon Science; Seattle (WA); On-site; USD 143,000 - 193,000; Full time

Benefits offered by this job

Health insurance

RSUs / stock options

401(k) matching

Paid time off

Parental leave

Job summary

Amazon Leo is seeking an Applied Scientist to join the founding Engineering and R&D team within Leo Infrastructure and IP Security. You will build statistical and behavioral models that baseline threat activity from telecoms and industrial data, while protecting sensitive data with privacy-preserving representations.

In this production-focused role, you will translate threat intelligence into robust detectors, document results for scientific and security audiences, and contribute to a

Qualifications

• 3+ years building models for business applications.
• PhD or Master with 4+ years in CS/CE/ML or related field.
• Experience with statistical modeling and large heterogeneous datasets.
• Fluency in Python; systems language such as Rust or C++ a plus.
• Experience with PyTorch or TensorFlow.

Responsibilities

• Build behavioral and statistical models that baseline normal activity across heterogeneous security telemetry.
• Design privacy-preserving representations of sensitive data and verify measurements remain accurate.
• Define methodology for difficult problems and justify approaches with evidence.
• Develop metrics and evaluation frameworks for model and detection performance.
• Contribute to neurosymbolic reasoning platform and ship production-quality components.
• Document work with rigorous scientific communication for both technical and security audiences.

Skills

Statistical modeling

Python

Time-series analysis

Anomaly detection

Behavioral baselining

Deep learning frameworks

Education

PhD or Master + 4+ years CS/CE/ML

Tools

PyTorch

TensorFlow

Rust

C++

Job description

Amazon Leo is seeking an Applied Scientist to join the founding Engineering and R&D team within Leo Infrastructure and IP Security. You will build statistical and behavioral models that baseline threat activity from telecoms and industrial data, while protecting sensitive data with privacy-preserving representations.

In this production-focused role, you will translate threat intelligence into robust detectors, document results for scientific and security audiences, and contribute to a