Software Development Engineer, Amazon Catalog services team, Amazon Catalog services team
Core
Design and build distributed systems to extract structured product knowledge from unstructured and semi-structured data sources (catalogs, reviews, images) to power Amazon's product representation.
Role type
SDE-II building large-scale distributed systems and LLM pipelines
Builds
Automated knowledge discovery pipelines, new schema patterns, and systems for novel attribute discovery
Domain
E-commerce, Retail, Large-scale Distributed Systems, LLMs
Deliverable
production ML models | product features
Required skills
Distributed systems design, High-scale software service design, Agile/continuous delivery, Object Oriented Design, Large-scale multi-tiered software development
Preferred skills
Full software development life cycle ownership, Code reviews, Source control management, Build processes, Testing, Operations
Technologies
C#, C++, Java, Perl, LLMs
Responsibilities
Design systems to extract structured knowledge from unstructured data, Build LLM prompts tuned for precision/recall, Build scalable knowledge discovery pipelines, Analyze and process large datasets from diverse sources, Define and evolve new schema patterns, Present work to leadership
Seniority
Senior, hands-on IC