Senior Applied Scientist, Capacity Forecasting & Optimization

Amazon Science; Seattle (WA); On-site; USD 167,000 - 226,000; Full time

Job summary

Amazon WorkSpaces capacity modelling team seeks a Senior Applied Scientist to own forecasting and optimization models that ensure compute, storage and networking resources are allocated cost-effectively with end-user performance in mind.

The role blends applied research with production systems, driving a scientific roadmap for capacity intelligence, turning reactive provisioning into predictive, self-optimizing planning across a global infrastructure.

Qualifications

• 3+ years building ML models for business applications.
• PhD, or Master's degree and 6+ years of applied research experience.
• Experience programming in Java, C++, Python or related language.
• Experience with neural deep learning methods and machine learning.

Responsibilities

• Define and drive the scientific strategy for capacity modelling establishing the research agenda for forecasting demand and allocating resources across a distributed infrastructure.
• Build advanced demand forecasting models that predict workspace usage across intraday to long-range horizons using signals like onboarding patterns seasonal trends and macro indicators.
• Design optimization frameworks for resource placement and cost-performance trade-offs balancing availability and efficiency.
• Develop causal and probabilistic models to understand demand drivers and quantify planning uncertainty.
• Architect simulation systems for what-if analyses and capacity planning under disruption scenarios.
• Pioneer integrated ML with operations research to jointly solve forecasting and resource allocation.
• Establish evaluation and monitoring to measure forecast accuracy capacity utilization and cost efficiency in production.

Skills

ML model development

Applied research

Programming: Java/C++/Python

Education

PhD, or Master's with 6+ years

Tools

R

scikit-learn

Spark MLLib

MxNet

TensorFlow

NumPy/SciPy

Job description

Amazon WorkSpaces capacity modelling team seeks a Senior Applied Scientist to own forecasting and optimization models that ensure compute, storage and networking resources are allocated cost-effectively with end-user performance in mind.

The role blends applied research with production systems, driving a scientific roadmap for capacity intelligence, turning reactive provisioning into predictive, self-optimizing planning across a global infrastructure.