Applied Scientist, Worldwide Grocery Stores

About the Role

Amazon's Worldwide Grocery Stores (WWGS), Data & Science team is seeking an Applied Scientist to join our Sales & Operations Planning (S&OP) and Supply Chain Science team. In this role, you will help build forecasting models that drive labor planning across the Amazon Grocery Network.

Key Responsibilities

• Develop, evaluate, and deploy components of demand and labor forecasting models, including statistical time-series, Bayesian, and machine-learning models with distributional objectives, with input and guidance from senior scientists.
• Translate business problems into well-defined scientific solutions with clear objectives, constraints, and success metrics, partnering with senior scientists on the more ambiguous ones.
• Analyze forecast performance and downstream impact on labor planning and capacity decisions; develop metrics that reflect business outcomes, not only forecast accuracy.
• Prototype and evaluate Generative AI approaches in forecasting workflows and help productionize successful ones.
• Partner with engineering teams to produce models, contribute to data pipelines, and build scalable, maintainable forecasting systems.
• Monitor deployed models, investigate performance issues, and continuously improve model quality and calibration.
• Communicate technical concepts and recommendations clearly through documentation, presentations, and design reviews with scientists, engineers, product managers, and business leaders.
• Contribute to the internal scientific community through knowledge sharing and, where appropriate, research publications.

Requirements & Tech Stack

• Proficiency in Python, including scientific computing and ML libraries (e.g., pandas, NumPy, scikit-learn).
• Experience with SQL and large-scale data processing on a modern data platform (e.g., Redshift, Spark, EMR, or equivalent data warehouse).

Qualifications

• Master's degree or above in Engineering, Computer Science, Machine Learning, Statistics, Physics, or related fields.
• Experience building machine learning models or developing algorithms for business application.
• Experience implementing algorithms using both toolkits and self-developed code.
• Experience with time-series forecasting or demand planning.
• Experience training and deploying models in a cloud environment (e.g., SageMaker, EC2, AWS Batch).
• Publications in peer-reviewed conferences or journals.