Apply on Employer Site

Amazon · 2 weeks ago

RF Systems Scientist, Amazon Leo

Redmond, WA

Full-time

Onsite

Mid, Senior Level

$136K/yr - $223K/yr

4+ years exp

Amazon is an initiative to increase global broadband access through a constellation of satellites. The role involves owning analytics, scientific research, and development of phased array systems to transform raw data into actionable insights, ensuring system performance for customer terminals and satellite-deployed terminals.

Artificial Intelligence (AI)DeliveryE-CommerceFoundational AIRetail

No H1B

U.S. Citizen Only

Responsibilities

Own metrics and data models that describe end-to-end calibration and system performance for customer terminals and satellite-deployed terminals, from factory test through field deployment

Design and implement ML and statistical methods (e.g., anomaly detection, drift detection, predictive failure models, classification/regression) to identify mis-calibration, degraded performance, and emerging issues in large fleets of terminals and arrays

Develop visualization and analytics tools (dashboards, reports, interactive notebooks) to help engineers quickly understand array performance, calibration residuals, and system margins across time, geography, and configurations

Work with antenna, RF systems, and calibration engineers to define quantitative acceptance criteria for calibration and system validation, and encode those criteria into automated checks and workflows

Design and run experiments and simulations that compare predicted vs. measured performance, closing the loop between link/array models and deployed hardware

Build and maintain data pipelines that ingest lab data, chamber results, manufacturing test data, and in-field telemetry into secure, high-quality datasets suitable for analysis and ML training

Prototype, test, and deploy machine learning and analytics applications in the cloud, partnering with software and systems teams to ensure solutions are scalable, maintainable, and integrated into existing tools and monitoring systems

Provide clear, data-driven recommendations to improve calibration algorithms, test strategies, and system design; communicate findings to technical and non-technical stakeholders

Mentor engineers and analysts in data best practices, experiment design, and interpretation of calibration and performance metrics

Qualification

Machine LearningData AnalysisRF SystemsProgramming JavaProgramming C++Programming PythonStatistical MethodsUnix/LinuxSoftware DevelopmentData VisualizationExperiment Design

Required

3+ years of building models for business application experience

PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience

Experience in patents or publications at top-tier peer-reviewed conferences or journals

Experience programming in Java, C++, Python or related language

Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing