Business Intelligence Engineer, Fulfillment Optimization

- Experience with data visualization using Tableau, Quicksight, or similar tools
- Experience using SQL to pull data from a database or data warehouse and scripting experience (Python) to process data for modeling
- Bachelor's degree or above in BI, finance, engineering, statistics, computer science, mathematics, finance or equivalent quantitative field
- Experience with AWS solutions such as EC2, DynamoDB, S3, and Redshift
- Knowledge of Microsoft Excel at an advanced level, including: pivot tables, macros, index/match, vlookup, VBA, data links, etc.

Amazon is an equal opportunities employer. We believe passionately that employing a diverse workforce is central to our success. We make recruiting decisions based on your experience and skills. We value your passion to discover, invent, simplify and build. Protecting your privacy and the security of your data is a longstanding top priority for Amazon. Please consult our Privacy Notice (https://www.amazon.jobs/en/privacy_page) to know more about how we collect, use and transfer the personal data of our candidates.

Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.
Do you want to make the invisible visible, turning complex model outputs into clear, actionable insights that shape how Amazon moves millions of packages?
We are looking for a Business Intelligence Engineer to own the analytics and explainability layer for Fulfillment Optimization systems that transform network-level plans into actionable signals, systems that tell fulfillment centers and trucks exactly how fast packages should flow, how capacity should be allocated, and how volume should be distributed across the network.

In this role, you will take loosely defined questions about model behavior, output quality, and business impact and refine them into analytical solutions that drive your team's decisions. You will design and own pipelines that decompose model outputs into interpretable signals across multiple planning and optimization systems, build dashboards and automated reporting that surface anomalies and inflection points, and develop the metrics that quantify how output shape and quality connect to fulfillment performance, transportation cost, and customer delivery promise. You will trace data lineage from the technical systems generating inputs through model transformation to downstream consumption, ensuring stakeholders understand not just what the numbers say but where they come from. You will work in SQL, Python, and AWS analytics services to deliver efficient, testable, and maintainable solutions that balance speed of delivery with long-term reliability.

What makes this role compelling is the direct line between your analysis and operational decisions. You are not reporting on historical trends. You are building the analytical foundation that tells us whether our models are producing the outcomes we expect and where opportunities exist to improve. You will partner with BIE and analytics teams across the organization to align on shared measurement approaches, connect your insights with broader network-level metrics, and enable self-service access to underlying data so stakeholders can explore without bottlenecks. You will collaborate with research scientists to validate model behavior, with engineering to instrument systems for observability, and with business stakeholders to recommend alternatives and anticipate future needs. If you enjoy refining loosely defined analytical problems, partnering across teams, and building the layer that connects model behavior to business outcomes, this is the role for you.

Key job responsibilities
- Design and own explainability frameworks that decompose model outputs across multiple Fulfillment Optimization systems into interpretable, actionable signals for science, engineering, and business stakeholders
- Build analytical pipelines and dashboards that monitor output shape and quality, detect anomalies, and quantify the relationship between model behavior and fulfillment performance
- Partner with BIE and analytics teams to align on shared metrics, enable self-service data access, and connect optimization insights with network-level reporting
- Trace data lineage from source systems through model transformation to downstream consumption, and translate findings into recommendations that inform team prioritization decisions