Description de l'offre
As a lead in e-Commerce, Amazon is building the authoritative knowledge base for every product in the world. With hundreds of millions of customers and billions of products, Amazon will offer a challenging but fun journey to turn this big and rapidly changing data into high-quality knowledge, and the great opportunities to impact various aspects of eCommerce.
The Product Graph team at Amazon, based in Seattle, is looking for scientists who love big data, who are passionate about understanding data from product profiles, reviews, and search log, and who are capable of inventing NLP, knowledge extraction, and search techniques that will leave no valuable data behind. Our applied scientists work closely with software engineers to put algorithms into practice. They also work in partnership with teams across Amazon to create enormous benefits for our customers.
We target at inventing advanced solutions for automatic knowledge collection and application. Our scientists will survey state-of-the-art techniques to increase coverage and quality of knowledge, conduct extensive empirical comparison of existing solutions, and invent new algorithms or models that push the envelope for product knowledge and for generic knowledge management. The research topics will include, but are not limited to, the following.
· Fact and feature extraction from product descriptions and reviews
· Knowledge extraction from the Web combining Open IE and Close IE techniques
· Search, question answering, and conversation using knowledge graph
· Human-in-the-loop knowledge learning
· Product trend discovery from web
· Knowledge verification from external sources
· PhD in Computer Science, Machine Learning, Statistics or a related field
· 3+ years of hands-on experiences in NLP, Search, Knowledge extraction, Machine Learning or a related field
· Algorithm development experience and problem solving ability
· Skills with Java, C++, or other programming language, as well as with Scala, MATLAB, Python or similar scripting language
Communication and data presentation skills.