Applied Scientist II, Worldwide Returns & Recommerce - Science

About the role

When a customer returns a package to Amazon, the request and package will be passed through our WWRR machine learning (ML) systems so that we could improve the customer experience, identify return root cause, optimize re-use, and evaluate the returned package. We operate at large scale and rely on state-of-the-art modeling techniques to power our ML models: XGBoost, BERT, Vision Transformers, Large Language Models.

What you'll do

• Help create everything from customer-facing and vendor-facing websites to the internal software and tools behind the reverse-logistics process
• Design, develop, and evaluate highly innovative models for Natural Language Programming (NLP), Large Language Model (LLM), or Large Computer Vision Models
• Use SQL to query and analyze the data
• Use Python, Jupyter notebook, and Pytorch to train/test/deploy ML models
• Use machine learning and analytical techniques to create scalable solutions for business problems

What you need

• 4–7 yrs of experience
• Machine learning
• Python
• Deep learning
• Data structures
• C++
• Java
• PhD or B.Tech or B.E.

Good to have

• IPR
• NLP
• Computer vision
• LLMs
• SQL
• PyTorch