San Francisco | California | United States
Pinterest helps people Discover and Do the things they love. We have more than 300M monthly active users who actively curate an ecosystem of more than 100B pins (ideas) on more than 1B boards, creating a rich human curated graph of immense value.
Technically, we are building out an internet scale personalized recommendation engine in 22+ languages, which requires a deep understanding of the users and content on our platform. As an engineer on the Pin Knowledge team, you’ll work on content classification, user modeling, personalization and ranking. Engineers of this team often make measurably positive impact on hundreds of millions of users with improved machine learning modeling and featurization breakthroughs.
Example projects of the team include:
1) Building end-to-end ML pipeline to discover the best text annotations for a Pin, and use them to improve Homefeed and Ads top-line metrics
2) Transform and automate our taxonomy expansion algorithms and pipelines using advanced ML and NLP techniques.
2) Develop state-of-the-art text embedding signals, as well as other featurization techniques for better model prediction performance
3) Analyze, compare and implement LR, GBDT and DNN models that are capable to serve our prod traffic in near real-time
4) Closely work with other product teams at Pinterest (Homefeed, Search, Ads etc) and conduct A/B experiments to improve various top-line metrics such as user engagement and revenue.
What you'll do:
What we're looking for: