Making a Difference with ML at Amazon

Speaker

Gheorghe Postelnicu

Abstract

Amazon’s vision is to be earth’s most customer centric company by thoroughly understanding our customers’ needs and desires. This talk will offer a sample of the types of Machine Learning challenges we face at Amazon to understand our customers at scale. It will then illustrate the practical trade-offs when designing and implementing practical ML algorithms.

Speaker Bio

Gheorghe Postelnicu has started his career as a research fellow with Harvard, working on Computer Vision problems in the field of Medical Imaging. He then joined Google, where he was one of the founding contributors of YouTube’s ContentID project, which provides copyright protection via fingerprinting techniques. Gheorghe joined Amazon 1 year ago in London, where he is leading a project focused on optimizing content acquisition for Prime Video.