Returning Candidate?

NLP Data Scientist

NLP Data Scientist

Job ID 
10611
Type 
Regular Full-Time
Company 
Fred Hutchinson Cancer Research Center
Location 
US-WA-Seattle
Category 
Information Technology

More information about this job

Overview

Cures Start Here. At Fred Hutchinson Cancer Research Center, home to three Nobel laureates, interdisciplinary teams of world-renowned scientists seek new and innovative ways to prevent, diagnose and treat cancer, HIV/AIDS and other life-threatening diseases. Fred Hutch’s pioneering work in bone marrow transplantation led to the development of immunotherapy, which harnesses the power of the immune system to treat cancer. An independent, nonprofit research institute based in Seattle, Fred Hutch houses the nation’s first cancer prevention research program, as well as the clinical coordinating center of the Women’s Health Initiative and the international headquarters of the HIV Vaccine Trials Network. Careers Start Here.

 

This is a data scientist and developer position within the data sciences group of the Hutch Data Commonwealth. An individual in this role provides programming, analytic, and data processing support for scientific projects in the domain of natural language processing (NLP).  Responsibilities include creating data pipelines and analytical data sets for projects pertaining to NLP; working with scientific investigators and other subject matter experts; defining and acquiring new data sources; developing software applications and tools for data processing and analysis.  In addition to automated data extraction, there is also a need for NLP capabilities in new language technology areas such as Chatbots.

NLP data scientists are also expected to take leadership in developing NLP as a particular applied data science area for HDC. This includes contributing to the concept, design and realization of more broadly applicable and scalable NLP solutions and making NLP capabilities more scalable and usable by Hutch research groups.

Responsibilities

Responsibilities include creating data pipelines and analytical data sets for projects pertaining to NLP; working with scientific investigators and other subject matter experts; defining and acquiring new data sources; developing software applications and tools for data processing and analysis.  In addition to automated data extraction, there is also a need for NLP capabilities in new areas such as Chatbots for behavioral intervention.

 

NLP data scientists are also expected to take leadership in developing NLP as a particular applied data science area for HDC. This includes contributes to the concept, design and realization of more broadly applicable and scalable NLP solutions and making NLP capabilities more scalable and usable by Hutch research groups.

Qualifications

Required

 

  • PhD (strongly preferred) or Master’s degree in computational linguistics, language technologies or computer science, with an NLP focus
  • 2 years or more experience in applied research and also development of NLP systems and solutions
  • Experience with and knowledge of open-source NLP software resources, for instance GATE, UIMA, OpenNLP, MedKATp, cTakes, etc.
  • Experience working with biomedical ontologies and resources (such as SNOMED, UMLS, BioPortal, etc.)
  • Machine-learning, particularly active learning
  • Data preparation and management
  • Programming proficiency in Python
  • Strong communication skills

Desired

  • NLP solution development in the biomedical domain
  • 5 years or more experience in applied research and also development of NLP systems and solutions
  • Data annotation processes, particularly semi-automated or crowd-sourced
  • Technical publications in the field