remote
Applied Scientist, Demand Forecasting - Amazon.com
Software Engineer
Lead the design and deployment of large‑scale foundation models for demand forecasting across millions of products, leveraging advanced time‑series and deep learning techniques on AWS infrastructure.
About the role
Key Responsibilities
- Architect and implement novel foundation models that generalize across diverse product catalogs and geographies.
- Develop and optimize training pipelines, data generation strategies, and evaluation metrics for large‑scale time‑series forecasting.
- Collaborate with data engineers to ingest, clean, and transform massive datasets into high‑quality training inputs.
- Deploy models to production on AWS, ensuring scalability, reliability, and low latency for real‑time forecasting.
- Conduct rigorous experimentation, analyze results, and iterate on model architecture to push state‑of‑the‑art performance.
Requirements
- Ph.D. or Master’s in Computer Science, Statistics, or related field with a focus on machine learning or time‑series analysis.
- Proven experience building and deploying deep learning models at scale, preferably in a cloud environment.
- Strong programming skills in Python and familiarity with frameworks such as PyTorch or TensorFlow.
- Hands‑on experience with AWS services (SageMaker, EC2, S3, Lambda) and CI/CD pipelines.
- Excellent analytical, problem‑solving, and communication skills.
Skills
pythonmachine learningdeep learningaws