ML Applied Scientist – Transportation Optimization

Amazon; Bellevue (WA); On-site; USD 143,000 - 193,000; Full time

Job summary

Amazon's Middle Mile Surface Research Science team is seeking an Applied Scientist to invent and build machine learning models that improve how Amazon plans and operates its transportation network. The role focuses on trailer imbalance forecasting and safety stock optimization to enhance equipment re-balancing.

You will translate business problems into modeling solutions, collaborate with product, engineering, and operations partners, and deliver models that influence decisions worth billions of

Qualifications

• PhD or Master’s degree plus 4+ years of science/engineering experience.
• Experience building ML models or developing algorithms for business applications.
• 1+ years of programming in Java, C++, Python, or related language.
• Experience with standard ML and statistical modeling tools (e.g., random forests, gradient boosting, LASSO, logistic regression).

Responsibilities

• Design and develop ML, forecasting, and other prediction models that enhance optimization and planning systems.
• Build models and algorithms from prototype to production-level systems.
• Translate ambiguous business problems into modeling approaches, and drive the technical design with product, engineering, and operations partners.
• Influence key business decisions through rigorous modeling and analysis.
• Communicate results and recommendations to scientific and business audiences.

Skills

ML model development

Programming in Java/C++/Python

Statistical modeling

Education

PhD or Master’s + 4+ years of experience

Tools

Java

C++

Python

Job description

Amazon's Middle Mile Surface Research Science team is seeking an Applied Scientist to invent and build machine learning models that improve how Amazon plans and operates its transportation network. The role focuses on trailer imbalance forecasting and safety stock optimization to enhance equipment re-balancing.

You will translate business problems into modeling solutions, collaborate with product, engineering, and operations partners, and deliver models that influence decisions worth billions of