"Clinical Research Repository Analyst"

Assist with cleaning, harmonization, aggregation and analysis of clinical data for a large ophthalmology repository. Extract information from unstructured electronic health record text using large language models (LLMs) and clinical natural language processing (NLP) techniques. Support researchers performing health services, population health and outcomes research related to vision. Perform data extraction; assist with data management and database building; maintain dashboards to coordinate data intake and processing; coordinate incoming data into the repository from different sources and staff members; obtain data directly from patient electronic health records to integrate into the repository; prepare grant proposal submissions; perform analyses for manuscripts and journal publications; and assist with regulatory, compliance, and IRB paperwork. Up to 100% remote work permitted.

Requires Master's degree in Statistics or Biostatistics + 2 years of experience: curating healthcare datasets of >20 million electronic health record (EHR) encounters and transforming raw EHR data into research-grade datasets; implementing natural language processing techniques and large language models on unstructured EHR text; applying transformer architectures adapted for biomedical applications; and using Python, SQL, PySpark, AWS cloud computing environment, Databricks, Git-based workflows, R and SAS.