Machine Learning Engineer, Knowledge
San Francisco, CA
Millions of people across the world come to Pinterest to find new ideas every day. It’s where they get inspiration, dream about new possibilities and plan for what matters most. Our mission is to help those people find their inspiration and create a life they love. As a Pinterest employee, you’ll be challenged to take on work that upholds this mission and pushes Pinterest forward. You’ll grow as a person and leader in your field, all the while helping users make their lives better in the positive corner of the internet.
On the Knowledge Core Signals team you will be building a brand new platform for extracting product metadata from web pages. You will be responsible for developing scalable, explainable and accurate ML solutions and you will have the opportunity to work on the full ML stack from efficiently extracting labels via human-in-the-loop approaches to modeling to deployment at scale. Your work will have a huge impact on Pinner’s shopping experience and drive future revenue growth via a more accurate product catalog.
What you'll do:
- Develop state-of-the-art algorithms for web information extraction
- Own, improve, and scale signals that enable ranking and product engineers to build deeper experiences to further engage Pinners
- Improve development velocity by building tooling for labelling data, evaluating model changes, explaining model decisions etc.
- Drive cross functional collaborations with partner teams such as Shopping who consume our signals
What we're looking for:
- 4+ years of industry experience
- Expert in Python and Java
- Experience working with big data technologies such as MapReduce/Hadoop/Hive/Presto/Spark
- Experience building and debugging large-scale distributed systems
- Experience with the full ML stack from modelling to deployment at scale
- [Nice to have] Familiarity with techniques for mining information from semi-structured data such as HTML e.g wrapper induction, XPaths