onsite
Data Scientist, Demand Forecasting - Amazon
Data Scientist
Data Scientist focused on building large‑scale foundation models for demand forecasting across millions of products, leveraging Python, deep learning, and AWS to advance time‑series research and production deployment.
About the role
Key Responsibilities
- Design and develop foundation models that predict demand for a vast, heterogeneous product catalog, including cold‑start items.
- Apply advanced time‑series and deep‑learning techniques (e.g., transformer‑based architectures) to improve forecast accuracy at scale.
- Collaborate with engineering teams to integrate models into production pipelines on AWS, ensuring low latency and high reliability.
- Conduct rigorous experimentation, A/B testing, and statistical validation to measure model impact on business metrics.
- Publish research findings and contribute to open‑source tools that advance the state of demand forecasting.
Requirements
- Strong proficiency in Python and experience with ML libraries such as PyTorch or TensorFlow.
- Deep knowledge of time‑series analysis, forecasting methods, and large‑scale model training.
- Hands‑on experience deploying machine‑learning solutions on AWS (e.g., SageMaker, EC2, Lambda).
- Proven ability to translate complex research into production‑ready systems.
- Excellent problem‑solving skills and a track record of publishing or presenting technical work.
Skills
pythonmachine learningdeep learningawspytorch