Clinical Data Engineer

Role overview

Build the data pipelines and quality processes that turn raw electronic health record (EHR) information into reliable, audit-ready datasets for clinical evidence studies. The work spans data ingestion, transformation, clinical data management, and final data lock, including adapting to differences between health systems. You will also help extract structured information from clinical text and collaborate with technical, clinical, and site teams to keep study data accurate and usable.

Responsibilities - Develop version-controlled Python and SQL pipelines to transform FHIR, HL7v2, and flat-file EHR extracts into structured study datasets. - Reconcile differences in site data models, mapping fields, harmonizing units, removing duplicates, and documenting derivation logic. - Apply language-processing methods to extract clinical variables from notes and reports, then validate the results. - Manage study data from ingestion and cleaning through quality checks and data lock; automate anomaly checks, validation, queries, and audit-trail review. - Maintain data dictionaries, electronic data capture forms, study specifications, and governance documents such as data management plans and procedures. - Coordinate with site IT and internal teams to plan feasible data capture and improve repeatable practices.

Requirements - At least five years in clinical research, real-world evidence, or health informatics. - Experience owning research database builds, data cleaning, quality control, and data lock. - Strong Python and SQL skills for automated data transformation and quality checks. - Hands-on experience converting raw EHR exports, such as FHIR, HL7v2, or flat files, into structured study data. - Familiarity with clinical coding systems, differing health-system data models, and reproducible, version-controlled pipelines. - Experience maintaining data management plans, procedures, runbooks, or mapping specifications, and familiarity with regulated-data requirements such as GCP, 21 CFR Part 11, or HIPAA. - Familiarity with language-processing tools for clinical text extraction.

Nice to have Experience with electronic data capture platforms such as REDCap, Castor, or Veeva; standardized clinical or health data models such as OMOP, CDISC, or PCORnet; and the structure of FHIR resources.

Benefits and work setup The listing describes a remote-first team across the United States and EU, with a team in Tel Aviv working in a flexible hybrid model. It mentions compensation, equity, and benefits; U.S. benefits include medical, dental, vision, retirement savings, and vacation. A separate benefits package is described for employees in Israel.