Applied Scientist, Worldwide Grocery Stores - Data and Science

Requirements

• PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
• 3+ years of building models for business application experience
• Knowledge of programming languages such as C/C++, Python, Java or Perl
• Knowledge of agile development and best coding practices including peer code reviews, and unit testing
• Experience deploying machine learning or optimization models into production systems.
• Experience in program management, logistics, operations, supply chain, transportation, or a related field
• Experience with AWS Services including EC2, Lambda, S3, DynamoDB, SQS
• Experience communicating technical concepts to non-technical audiences
• Familiarity with simulation-based optimization and discrete-event simulation
• Experience with causal inference, econometrics, or machine learning (e.g., neural networks, reinforcement learning)
• Track record of publishing research at peer-reviewed conferences or journals
• Demonstrated ability to work semi-autonomously, gathering business requirements and translating them into scientific solutions
• Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.
• USA, WA, Seattle - 142,800.00 - 193,200.00 USD annually

Additional Information

Amazon's Worldwide Grocery Stores (WWGS), Data & Science team is seeking an Applied Scientist to join our under the roof (UTR) Science team, focused on improving outbound pick efficiencies across the Amazon Grocery Network. In this role, you will build optimization and simulation models that directly reduce operational costs and improve associate productivity in warehouse picking operations. This role owns the development and deployment of mathematical optimization models for pick planning, inventory placement, and warehouse layout design. You will formulate ambiguous business problems as concrete scientific models, develop and deploy production-grade solutions, and work closely with engineering partners, product owners, and business stakeholders to deliver measurable impact. Because UTR operations are complex and inter-connected (e.g., inbound stow vs. outbound pick), this role requires a strong understanding of these relationships and the ability to make trade-offs at the system level. You will interface directly with non-technical product owners and business leaders, manage expectations, and take an active part in influencing the feature roadmap. Key job responsibilities - Design, develop, and deploy mathematical optimization models (e.g., Mixed Integer Programming, meta-heuristics) to improve outbound picking efficiency, including pick planning and inventory placement. - Build simulation models to evaluate warehouse layout designs, test optimization solutions offline, and answer strategic what-if questions. - Formulate complex, ambiguous business problems into well-defined scientific solutions with clear objectives and constraints. - Collaborate with engineering teams to productionize models, establish data pipelines, and create scalable architectures. - Track solution performance post-deployment, identify issues through deep dives, and iteratively improve model quality. - Communicate technical concepts clearly to diverse stakeholders - scientists, engineers, product managers, and business leaders - through documentation, presentations, and design reviews. - Author peer-reviewed research papers on developed models and contribute to the internal scientific community.

Your Match

How well this role fits your profile.

Company Intel

What employees say

Worked at Amazon.com Services LLC? Share your experience