Software Development Engineer, Amazon Catalog services team, Amazon Catalog services team

As a Software Development Engineer, do you want to help transform how Amazon understands and represents products by unlocking critical information from previously untapped data sources? The Attribute Knowledge Mining team in Amazon Catalog Services is core to providing and exposing complete and concise product details across the Amazon website. We provide attribute knowledge consumed by multiple partner teams across retail organizations to power seller and buyer experiences. My team owns deep integration with large language models, full stack systems to automatically mine attribute knowledge, and the infrastructure to share mined knowledge with various teams within Amazon retail. Our team is based out of Seattle.

We are looking for Software Development Engineers with experience in distributed systems to join our team! As a Software Development Engineer (SDE-II), you will work on a new initiative to extract critical product information that goes beyond what our current catalog schema supports. We are building new systems to discover, structure, and surface novel product knowledge from diverse and previously untapped data sources, enabling catalog innovation that improves both existing customer experiences and emerging agentic ones. This is an opportunity to work on high-visibility initiatives that will shape the next generation of product understanding at Amazon. You will work with several senior software development engineers and principal engineers regularly. We maintain a high bar for operational and software engineering excellence, which helps keep our operational load manageable. Our software development engineers are customer-focused and detail-oriented. We are a fun-loving team with a collaborative and supportive culture.

The ideal candidate will have distributed systems, high-scale software service design and implementation, and agile/continuous software delivery experience. You are a Software Development Engineer who enjoys owning software services, loves adopting new technology, is customer-centric, and values delivering software with high quality.

Key job responsibilities

• Design and build systems to extract structured knowledge from unstructured and semi-structured data sources that extend beyond existing catalog schema
• Build LLM prompts and tune them to meet Precision and Recall requirements for novel attribute discovery
• Build scalable, efficient, and automated knowledge discovery pipelines that surface new product dimensions for both conventional and agentic consumers
• Analyze and process large amounts of data to identify and extract valuable information from diverse sources (e.g., product catalog, customer reviews, search queries, product images, external knowledge bases)
• Define and evolve new schema patterns to represent previously uncaptured product knowledge
• Actively participate in idea and roadmap generation

Effectively present work to all levels of leadership

• Be an effective collaborator in a cross-functional team of SDEs, Technical Program Managers, and Product Managers