Senior Applied Scientist, Capacity Modeling for WorkSpaces

Amazon Web Services (AWS); Seattle (WA); Vor Ort; USD 167.000 - 226.000; Vollzeit

Benefits dieser Stelle

Health insurance

RSUs

Paid time off

Parental leave

401(k) matching

Zusammenfassung

Amazon Development Center U.S., Inc. in Seattle is seeking a Senior Applied Scientist to own capacity modelling for Amazon WorkSpaces.

You will design, build, and continuously improve forecasting and optimization models to ensure the right compute, storage, and networking resources are available at the right time in the right regions at the lowest possible cost, without compromising the user experience. This is a high-impact, individual contributor role blending applied research with production

Qualifikationen

• PhD or Master’s + 6+ years of applied research experience.
• 3+ years of building ML models for business applications.
• Experience with Java, C++, Python or related languages.

Aufgaben

• Define and drive the scientific strategy for capacity modelling across WorkSpaces.
• Build advanced forecasting models for workspace usage across time horizons.
• Design optimization frameworks for resource placement, mix and pre-warming strategies.
• Develop causal and probabilistic models to understand demand drivers and uncertainty.
• Architect simulation systems for what-if analyses and capacity planning.
• Pioneer ML integration with operations research for joint demand prediction and resource allocation.
• Establish monitoring to measure forecast accuracy, capacity utilization and cost efficiency.
• Translate model outputs into actionable leadership recommendations.

Kenntnisse

Machine learning

Python

Java

C++

Applied research

Ausbildung

PhD

Master's degree + 6+ yrs experience

Tools

R

scikit-learn

Spark MLLib

MxNet

TensorFlow

NumPy

SciPy

Jobbeschreibung

Amazon Development Center U.S., Inc. in Seattle is seeking a Senior Applied Scientist to own capacity modelling for Amazon WorkSpaces.

You will design, build, and continuously improve forecasting and optimization models to ensure the right compute, storage, and networking resources are available at the right time in the right regions at the lowest possible cost, without compromising the user experience. This is a high-impact, individual contributor role blending applied research with production