Description
Amazon's Selection Monitoring team is responsible for building and operating large-scale data processing systems that power catalog intelligence across Amazon. Our systems process billions of products from multiple data sources—both real-time crawler feeds and pre-computed datasets—to create comprehensive, high-quality product information that drives business decisions across Amazon. We apply parallel processing, machine learning, and deep learning algorithms to evaluate and enrich product data at global scale. The datasets and insights produced by our team enable teams across Amazon to make data-backed decisions that improve customer experience.

Our work involves building state-of-the-art data processing pipelines and Information Retrieval (IR) systems that handle diverse data streams and automatically create structured entities from unstructured/semi-structured data. We constantly stretch the boundaries of large-scale distributed systems, streaming and batch p...