Applied Scientist II, Books Data Quality
Role details
Job location
Tech stack
Job description
Passionate about books? The Amazon Books team is looking for a talented Applied Scientist II to help invent, design, and deliver science solutions to make it easier for millions of customers to find the next book they will love. In this role, you will
- Be a part of a growing team of scientists, economists, engineers, analysts, and business partners.
- Use Amazon's large-scale computing and data resources to generate deep understandings of our customers and products.
- Build highly accurate models (and/or agentic systems) to detect and correct errors in Books metadata.
- Design, implement, and deliver novel solutions to some of Amazon's oldest problems.
Key job responsibilities The role is focused on ensuring our book (meta)data is as accurate as possible. As part of that you will be responsible for designing, developing and evaluating state-of-the-art systems that detect and correct errors by contrasting book information from different sources. As part of this goal, you will identify and solve complex science problems in this space by using and inventing tools across several disciplines, including agentic systems, deep learning, natural language processing (NLP), knowledge graphs/taxonomies, recommender systems, and reinforcement learning (RL). As part of the team, you will be exposed to all of these areas and have opportunities to hone and apply your skills across our problem space.
A day in the life Day-to-day work varies over the course of a project, but includes model design, development, training, tuning, testing, and deployment, as well as identifying science solutions to business problems, acquiring and understanding data sources, and designing and analyzing experiments testing your solutions.
About the team The team consists of a collaborative group of scientists, product leaders, and dedicated engineering teams. Our aim is to maintain the world's most accurate and descriptive set of books metadata, where every title in our catalog is uniquely characterized via a set of high-quality, concise attributes. We believe this is a foundational capacity for any bookstore. We work with sister teams to leverage our systems to drive a diverse array of customer experiences, owned both by ourselves and others, that enable customers to easily identify their ideal next read.
Requirements
PhD, or a Master's degree and experience in CS, CE, ML or related field
-
Experience in building models for business application
-
Experience in patents or publications at top-tier peer-reviewed conferences or journals
-
Experience programming in Java, C++, Python or related language
-
Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing
-
Experience using Unix/Linux
-
Experience in professional software development
