As member of Periscope’s product development team you will be responsible for expanding our Natural Language Processing (NLP) capabilities with regards to classifying, categorizing and searching procurement data. Periscope has an existing NLP framework for classifying Government bids according to National Institute Government Purchasing (NIGP) codes. We are looking to extend that ability to include requisition and purchase order line item data. In addition, you will be developing search algorithms and mechanisms for performing free text searching of procurement related documents. Once developed these methods will need to be productized and made usable by Periscope’s operational teams to produce content for our SaaS and subscription data products on an on-going and cost effective basis.
Required Experience • Transforming unstructured text into database representations that can be browsed, searched, and clustered. • Experience with NLP statistical methods for classification and categorization • Working knowledge of NLP tools such as Lucene, Solr, OpenNLP, and Mahout • Proficiency with the Java programming language • Knowledge and ability to work with relational databases and SQL • Demonstrated success in in applying NLP techniques in previous positions • Bachelor’s degree in Computer Science, Linguistic, Statistics or other Data Science discipline
Desired Experience • Working knowledge of non-relational databases such as MongoDB, Cassandra, HBase, Neo4j
