Job Description

Help advance the development of our models for disambiguation, tagging, linking, clustering, and deduplication. Our goal is industry-leading accuracy of the citation graph and the systems that build it. Develop a deep understanding of our algorithms and systems, and develop a deep understanding of the scholarly data we work with. This is necessary to enable identification of opportunities for fundamental improvements in our algorithms, and to enable identification of root causes of problems. Work with our content evaluation team to build large-scale gold sets that are the basis for measuring and improving the recall and precision of our systems. This includes devising new ways to sample data, to focus on areas targeted for improvement. Work on varied projects to extend our systems to new content types and new application areas. Advance the automation and reliability of our core data science processes. Work closely with our software engineers to drive experiments, implementations, optimization, and new features.