Text and Linguistic Processing Specialist

Overview:
We are a fast-growing company thriving through the economic downturn by providing a unique and much needed travel service based on intelligent semantic processing of millions of travel reviews. We are looking for an outstanding individual who not only has an academic background with a variety of text and linguist processing algorithms, but also is an outstanding engineer who can effectively bring these technologies to market. Candidate will have a direct impact UpTake's core data acquisition and processing infrastructure enabling us to scale our search index to massive scale.

The Text and Linguistic Specialist role involves clustering/classification, topic identification, named entity tagging, lexicon acquisition and pattern identification from large corpora. The ideal candidate will have a PhD (or equivalent) in Computer Science or related field with experience in natural language processing, computational linguistics, or information retrieval/extraction. Strong programming skills are required. At least two years of experience working with real life NL systems is required. A strong research record is a plus. We look for people who are flexible, learn quickly, and love getting into the details.

Responsibilities:
Create world-class systems using machine learning techniques to improve UpTake product clustering/classification, lexicon acquisition, data sourcing, de-duplication, and ranking algorithms. The successful candidate is very hands on developing Java code and can apply the 80/20 rule to make quick, pragmatic decisions that provide dramatic consumer benefits.

Experience (required):
5+ years industry experience and world-class expertise applying machine-learning to classification, ranking, information extraction and other NLP tasks, using an iterative process based on human supplied training data.
5+ years experience and very strong engineering skills in Java development including intensive and highly performant SQL.
Thorough knowledge of algorithms and best practices for working with SVM's, decision trees and similar classification and ranking tools.
Likes to work in a collaborative team environment. Is very familiar with common collaboration and code/build management tools such as SVN, Ant, Maven.
Ability to shift gears quickly in a start-up environment.

Experience (ideal):
Experience with information retrieval/search indexing tools such as Lucene and Solr.
Knowledge of text analysis, entity extraction and tools to support these tasks.
Rich experience with web application technologies: Web services, XML, SOAP, SAX, Ruby on Rails, Active Record and/or J2EE technologies including EJB, Spring, Hibernate.