Applied Scientist, Fulfilled-by-Amazon (FBA)

About the role

FBA Science seeks an Applied Scientist to invent and build optimization models and algorithms that improve how Amazon plans and places seller inventory across its worldwide fulfillment network. FBA moves the inventory of hundreds of thousands of sellers through a multi-echelon network of origin storage, national and regional distribution, and fulfillment centers — putting the right inventory in the right place, on time and at low cost. Operating this network is a constant stream of decisions: how much a seller should send, and where and when it should flow, all under scarce receiving and storage capacity. These decisions are not made alone — sellers choose what to send and how to respond to the options and incentives offered, so the network must be planned and seller behavior shaped together. The strategy is to make these decisions with science-driven technology, inventing new approaches and algorithms where existing techniques rarely fit Amazon's scale and unique business needs.

As an Applied Scientist, you'll develop optimization models and algorithms across FBA's inventory planning and placement systems, initially focusing on joint replenishment and placement decisions. Your models will impact business decisions worth billions of dollars and improve the experience of every FBA seller.

Sellers play a vital role in Amazon's ecosystem, integral to the mission of offering Earth's largest selection, lowest prices, and fastest delivery speed. FBA enables third-party sellers to outsource order fulfillment to Amazon and leverage Amazon's world-class facilities for fast delivery. With commitment to taking on more of the supply chain and operational complexities, Amazon provides an end-to-end suite of supply chain services empowering sellers to reliably transport products from manufacturing sites to customers worldwide. The FBA team manages warehousing, inventory management, fulfillment and pricing, recommendation services for sellers, and internal resource management systems. The team learns seller behavior, understands seller experience, recommends actions, designs seller policies and incentives, and develops science products and services that empower sellers to grow. Solutions leverage operations research, economics, machine learning, statistics, and data analytics, with a culture centered on rapid prototyping, rigorous experimentation, and data-driven decision-making.

Responsibilities

• Own the development of replenishment, placement, and transportation-planning algorithms that decide how a seller's inventory flows across Amazon's fulfillment network.
• Design and implement large-scale optimization models and algorithms for complex inventory-planning problems, and the prediction and estimation layer they depend on.
• Partner closely with Product Managers and engineers to define high-impact problems, translate ambiguous business challenges into well-scoped science initiatives, and deliver actionable, science-driven solutions.
• Build and deploy science solutions into production pipelines, ensuring models operate reliably at scale across a network serving hundreds of thousands of sellers.
• Own a science area with significant scope, impact, and high visibility, touching millions of products, hundreds of thousands of selling partners, and tens of millions of customers.
• Operate in the seller's critical path, involved in every step from idea generation and business analysis through research to development and deployment of production-grade models.
• Move between optimization and behavior modeling; make decisions about methodology, model architecture, and technology choices, striving for simplicity and demonstrating judgment backed by mathematical rigor.
• Work closely with product managers, engineers, and fellow scientists; collaborate with the broader science community across Amazon.
• Be entrepreneurial, wear many hats, and work in a fast-paced, high-energy, highly collaborative environment that values people who deliver results, know their subject deeply, and are eager to learn new areas.

Requirements

• 2+ years of building models for business application experience
• Experience in patents or publications at top-tier peer-reviewed conferences or journals
• Experience programming in Java, C++, Python or related language
• Demonstrated ability to build complex optimization models from scratch and take them to production
• PhD in Operations Research, Industrial Engineering, Computer Science, Statistics, Applied Mathematics, Economics, or a related quantitative field

Qualifications

• Track record of translating ambiguous business problems into well-defined science solutions with measurable impact
• Proven ability to work effectively across product, engineering, and science teams
• Experience with supply chain optimization, demand forecasting, inventory management, or transportation/logistics algorithms
• Experience with reinforcement learning applied to sequential decision-making in operations or supply chain contexts
• Experience with product selection or assortment optimization for capacity-constrained systems
• Strength in mechanism design, auction theory, or game theory, particularly in settings involving strategic agents, capacity allocation, or market-based resource allocation

Pay

Base salary range: $142,800 – $193,200 USD annually (USA, WA, Bellevue). Package includes sign-on payments and restricted stock units (RSUs). Final compensation determined by experience, qualifications, and location.

Benefits

• Health insurance (medical, dental, vision, prescription)
• Basic Life & AD&D insurance and option for Supplemental life plans
• EAP, Mental Health Support, Medical Advice Line
• Flexible Spending Accounts
• Adoption and Surrogacy Reimbursement coverage
• 401(k) matching
• Paid time off
• Parental leave

Company: Amazon.com Services LLC | Job ID: A10583157