NLP / LLM Data Scientist

This is a fully remote position, open to applicants in New York.

📋 Description

• Develop natural language processing (NLP), large language model (LLM), and other machine learning (ML) pipelines to extract labels from healthcare-related text data and store them in scalable data models.

• Execute queries on intricate healthcare source systems, including electronic medical records (EMRs), semi-structured reports, and free-text clinical documentation.

• Identify essential data components and create as well as enhance datasets for real-world evidence analyses and training of AI algorithms.

• Take ownership of data extraction, wrangling, labeling, and quality control tasks related to analytical datasets.

• Implement current NLP and generative AI techniques for applicable use cases.

• Design, test, validate, analyze, and integrate multimodal data structures from diverse source systems.

• Produce code and documentation for high-quality, HIPAA-compliant data products.

• Diagnose issues and ensure the accuracy, integrity, and validity of data.

• Support the technical product team and enhance data-related product offerings.

• Communicate abstraction methods, findings, and recommendations to both technical and clinical audiences.

• Report directly to the Data Science Manager under the leadership of the Head of Data.

• Participate in occasional in-person company workdays, approximately quarterly.

⛳️ Requirements

• An advanced degree in a quantitative discipline (e.g., Data Science, Biomedical Informatics, Computer Science, Biostatistics), or a B.S. with a minimum of 5 years of relevant professional experience.

• At least 2 years of experience in data science and machine learning, specifically in constructing pipelines for extracting and curating unstructured and semi-structured data using advanced ML and AI methodologies.

• Proficiency in Python and SQL, including familiarity with ML/NLP libraries such as PyTorch, TensorFlow, and HuggingFace.

• Knowledge of contemporary applied LLM techniques on real-world datasets.

• Strong skills in technical writing, editing, and communication.

• Exceptional organizational abilities with a capacity to manage multiple projects and meet deadlines.

• Experience with Git and version control systems.

• Understanding of encryption methods.

• Background in querying enterprise data warehouses (EDWs) or databases and generating healthcare reports or analytics.

• Familiarity with electronic medical record systems, including Epic, Cerner, or Allscripts.

• Experience with medical ontologies.

• Familiarity with DICOM or other imaging modalities.

• Experience with Amazon Web Services (AWS).

• History of publishing work in peer-reviewed journals.

• Ability to work in the US and authorization to work full-time in the US is required in the application form.

🏝️ Benefits

• Offers equity.

• Provides bonuses.

• Allows for remote work and flexible working hours.

• Comprehensive wellness benefits, including healthcare, dental, vision, paid time off (PTO), sick days, and more.

• Professional development days to enhance your skills.

• A collegial work environment.

• A balanced approach to focused work time and easy access to team members for collaboration.

• A mission-driven company dedicated to improving patient care.