Data Scientist

Boston VA Research Institute, Inc. (BVARI)- NLP Data Scientist

A VA Boston-based research group affiliated with Harvard Medical School and the BU School of Medicine has an opening for a Natural Language Processing (NLP) data scientist. In this position, you will collaborate with our team on the development of algorithms for data extraction and classification of healthcare information in large-scale VA datasets. You will join a strong, collegial, friendly, and talented team of computer scientists, statisticians, and clinicians.

What You’ll Do

• Work closely with the VA’s electronic health record (EHR) database, which contains comprehensive clinical information on over 22 million patients (2 trillion rows, 22,000 columns of data), including large amounts of both structured and unstructured data
• Design, develop, test, and maintain robust and clinically relevant implementations of NLP algorithms for clinical research and applications
• Design, develop, test, and maintain automated, reliable data pipelines that enable NLP algorithms to be developed and deployed at scale
• Develop improved methodology in relation to healthcare data analysis and clinical implementation
• Collaborate with a range of researchers, including NLP scientists, computer scientists, statisticians, and clinicians
• Publish papers on our findings, systems, and methodology

• Example projects include:
• After our team identifies a need for the extraction of specific staging elements from unstructured medical notes for a cohort of patients with multiple myeloma, you will develop an algorithm to extract this information at scale and return results in a human- and machine-readable format for incorporation into downstream analyses.
• After a clinical stakeholder approaches our team with a request for the development of an algorithm to better identify changes in prognostic indicators for prostate cancer, you will work with the stakeholder to generate training and testing datasets and create a large language model-based pipeline that ingests unstructured notes to make predictions of patient changes over time.

Who You Are

• Hold a bachelor’s, master’s, or PhD in computational linguistics, computer science, statistics, engineering, informatics, AI or related field
• Significant experience with NLP methodology including information extraction and classification with large language models, neural networks, and/or rule-based algorithms
• Experience with natural language data annotation and dataset development
• Significant software development experience and strong programming skills in Python
• Willingness to learn the VA’s complex relational data model and interact directly with this database
• Strong communication and collaborative research skills
• Ability to drive projects independently with moderate support
• Close attention to detail
• Experience with developing software for use in clinical care is a plus
• Experience with electronic medical record data or clinical databases is a plus
• Experience with R is a plus

The employee must be a resident of Massachusetts upon the start date.

Please note we are unable to provide work authorization and/or visa sponsorship.

Work Environment

This job operates in a professional office environment. This role routinely uses standard office equipment such as computers, phones, photocopiers, filing cabinets and fax machines.

Physical Demands

The physical demands described in this job description are representative of those that must be met by an employee to successfully perform the essential functions of this job.

While performing the duties of this job, the employee frequently is required to stand; walk; use hands; and reach with hands and arms.

Selective Service

If you are male application born after December 31, 1959, you must certify that you have registered with the Selective Service System or are exempt from having to do so under the Selective Service Law.

This position requires the ability to occasionally lift office products and supplies, up to 20 pounds.

Position Type/Expected Hours of Work

This is a full-time position, and hours of work and days are Monday through Friday, 8:30 a.m. to 5 p.m.

Travel

No travel is required for this position. Optional travel to scientific meetings may occur from time to time.

Work Authorization/Security Clearance

An employee in this position must complete all appropriate background checks at the time of hire and periodic reappointment.

Other Duties

Please note this job description is not designed to cover or contain a comprehensive listing of activities, duties or responsibilities that are required of the employee for this job. Duties, responsibilities, and activities may change at any time with or without notice.

Equal Opportunity Employer

Boston VA Research Institute provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state, or local laws. This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, transfer, leaves of absences, compensation, and training.

Pay Range

Minimum $115,000.00, Midpoint $135,000, Maximum $155,000.00

Salary is based on related experience, expertise, and internal equity; generally, new hires can expect pay between the minimum and midpoint of the range.