Junior NLP Data Scientist

Position Overview

SteerBridge is seeking an NLP Data Scientist to support the Modern Disability Claims program, applying natural language processing and machine learning to extract, structure, and analyze medical and claims data in support of VA disability claims adjudication. This role blends deep NLP/transformer expertise with hands-on experience in healthcare and claims data.

Key Responsibilities

• Extract medical and claims-relevant data using NLP; tune models with VA datasets

• Build and maintain NLP pipelines to support automation and analytics in claims adjudication

• Collaborate with VA stakeholders to define data science requirements and deliver impactful solutions

• Ensure quality control, model accuracy, and performance through testing and iteration

• Document data processing workflows, model design, and tuning procedures

• Contribute to integration of NLP models within VA systems and infrastructure

Required Qualifications

• U.S. Citizenship required

• Must hold, or be able to obtain, a Public Trust clearance

• Bachelors in Applied Mathematics, Statistics, Computer Science, or a related discipline — or equivalent experience

• 1-3 years of experience with Python, Amazon Comprehend Medical, Google Cloud NLP, and transformers

• Familiar with SQL, Jupyter notebooks, and collaborative coding environments

• Ability to communicate complex data science concepts to technical and non-technical audiences

• Demonstrated ability to manage and deliver data science projects in a government or healthcare setting

Preferred Qualifications

• RAG, Embedding, Vector DB, Hugging Face transformers, BERT, BART, LLMs

• Strong understanding of healthcare-related data including EMRs, claims, clinical codes (ICD, CPT), and terminology

• Experience working in cloud environments (AWS, Google Cloud, or Azure)