Data Scientist, Demand Forecasting, SCOT
Amazon.com
Are you looking for an environment where you can drive innovation, apply state-of-the-art machine learning techniques, and tackle real-world problems at massive scale? Do you want to shape the future of Amazon’s Retail business by designing and deploying deep learning models for time series forecasting? If so, join the Amazon Demand Forecasting Science team! As part of this dynamic team, you will create and implement novel neural network architectures to develop the next generation of foundation time series models, directly influencing how Amazon operates at a global scale.
Key job responsibilities
Design new deep learning algorithms and creative approaches to push time series forecasting performance beyond the current state-of-the-art.
Work cross-functionally with product managers, software engineers, and scientists to build end-to-end solutions that are deployed at scale in Amazon’s production systems.
Engage with the broader scientific community at Amazon and beyond - collaborate with academic researchers, contribute to publications, and present your work at leading conferences (e.g., NeurIPS).
A day in the life
You will deep dive into massive Amazon time series datasets, leveraging Python and PySpark to conduct exploratory data analysis. You will prep the data pipeline - writing Python code to train, evaluate, and debug the latest deep learning models. You will design novel neural network architectures, brainstorming with fellow scientists and engineers on ways to push the boundaries of foundation time series modeling. You may explore and benchmark open-source solutions, identifying opportunities to enhance Amazon’s forecasting capabilities. You will document your discoveries and prepare them for internal knowledge-sharing sessions or external conferences, ensuring that your innovations help shape the future of demand forecasting - both within Amazon and the broader research community.
About the team
We are responsible for accurately predicting sales for millions of products worldwide. Our work reduces costs, drives lower prices, and improves selection for customers - all while leveraging unprecedented volumes of data that only Amazon can offer.
Key job responsibilities
Design new deep learning algorithms and creative approaches to push time series forecasting performance beyond the current state-of-the-art.
Work cross-functionally with product managers, software engineers, and scientists to build end-to-end solutions that are deployed at scale in Amazon’s production systems.
Engage with the broader scientific community at Amazon and beyond - collaborate with academic researchers, contribute to publications, and present your work at leading conferences (e.g., NeurIPS).
A day in the life
You will deep dive into massive Amazon time series datasets, leveraging Python and PySpark to conduct exploratory data analysis. You will prep the data pipeline - writing Python code to train, evaluate, and debug the latest deep learning models. You will design novel neural network architectures, brainstorming with fellow scientists and engineers on ways to push the boundaries of foundation time series modeling. You may explore and benchmark open-source solutions, identifying opportunities to enhance Amazon’s forecasting capabilities. You will document your discoveries and prepare them for internal knowledge-sharing sessions or external conferences, ensuring that your innovations help shape the future of demand forecasting - both within Amazon and the broader research community.
About the team
We are responsible for accurately predicting sales for millions of products worldwide. Our work reduces costs, drives lower prices, and improves selection for customers - all while leveraging unprecedented volumes of data that only Amazon can offer.
Confirm your E-mail: Send Email
All Jobs from Amazon.com