We're building an exciting personalization and recommendation platform. Come and join us and hack on bleeding edge NLP and ML research applied to web-scale datasets in search, information extraction, clustering and collaborative filtering.
You'll work on expanding our existing classification, filtering, and content extraction technology. Research and prototype new methods for adaptive learning and relevance determination and ship production ready code by collaborating with the rest of our backend team, each of them passionate and opinionated engineers with their collective experience spanning software engineering, large multi-site databases and platform scalability.
We use a number of languages and open source components for our platform. You should enjoy working with some or all of the following:
Git/GitHub for version control
Multi-threaded Python (the majority of our code), Java, C/C++
Unit tests, Mocking, Continuous integration
Multiple production deployments on a daily basis
You should have solid experience with machine learning and numerical analysis toolkits like
Strong background in NLP (tagging, chunking, semantic extraction), Machine Learning (clustering, classification) and information retrieval (lucene, solr, etc)
Sound programming fundamentals in Python and optional experience in C, C++, Java, R, Scala, Clojure, etc.
Search relevance experience a plus
Entrepreneurial spirit and strong drive to contribute to all aspects of the product and company
Experience working in a UNIX/Linux environment
Competitive Salary + Stock Options + Comprehensive Benefits + 401K + Generous Vacation Program