Senior Data Scientist - Capacity Planning & Forecasting

Amazon Web Services (AWS); Dallas (TX); On-site; USD 159,000 - 215,000; Full time

Job summary

Amazon Web Services, Inc. in Dallas, TX is seeking a data scientist to build forecasting, optimization, and predictive models that improve support operations and cost efficiency.

You will partner with data engineering, product, and finance teams to drive data-driven decisions across the network. The ideal candidate has 5+ years of data querying and Python/R experience, strong modeling skills including multinomial logistic regression, and experience with visualization tools.

Qualifications

• 5+ years of experience with data querying languages (e.g., SQL) and scripting languages (e.g., Python) or statistical software (e.g., R, SAS, Matlab).
• 4+ years of data science experience.
• Experience with statistical models such as multinomial logistic regression.

Responsibilities

• Establish data management and strategy frameworks for data collection, storage and quality.
• Collaborate with cross-functional teams to identify data challenges and develop data-driven solutions.
• Conduct research to understand data needs and assess infrastructure gaps.
• Leverage large-scale data processing frameworks (e.g., Spark, Hadoop) for model training.
• Evaluate and improve machine learning models based on real-world feedback.
• Develop ML models that drive business value and forecast outcomes.
• Analyze data domains (customer, market, financial, operations) to inform strategy.
• Identify bottlenecks and opportunities to reduce costs and improve customer outcomes.

Skills

SQL

Python

R

SAS

Matlab

Multinomial logistic regression

Tools

AWS QuickSight

Tableau

R Shiny

Job description

Amazon Web Services, Inc. in Dallas, TX is seeking a data scientist to build forecasting, optimization, and predictive models that improve support operations and cost efficiency.

You will partner with data engineering, product, and finance teams to drive data-driven decisions across the network. The ideal candidate has 5+ years of data querying and Python/R experience, strong modeling skills including multinomial logistic regression, and experience with visualization tools.