Clinical Data Engineer
About this role
Purpose: The Clinical Data Engineer will be an individual contributor to the Medical Affairs department. The role will encompass the development and pipeline management and curation of clinical datasets for internal reports, external presentations, manuscripts and publications, and to inform future clinical trial design.
This is a remote role requiring valid work authorization in the U.S. without requiring employer sponsorship.
Responsibilities:
Develop and maintain ELT/ETL pipelines for daily and weekly electronic health record (EHR) data extracts.
Migrate structured CSV data into databases/data warehouse/data lake to enable efficient querying
Develop dashboards for tracking the performance and effectiveness of the IntelliSep solution in improving clinical outcomes, operational efficiency, and financial performance and provide insights into customer-related metrics and the potential impact on patient outcomes and hospital reimbursement.
Standardize tables and data artifacts towards a canonical data schema.
Develop documentation and methodologies for infrastructure.
Handle protected health information (PHI) and other sensitive clinical data in accordance with HIPAA and Cytovale's data privacy and security policies, ensuring data integrity, traceability, and appropriate access controls throughout the data pipeline.
Maintain version control for code and data.
Support quality improvement activities for customers by building systems and tools for post-implementation data analysis
Qualifications:
Bachelor’s degree in computer science, electrical engineering, or related field.
3+ years of industry related experience, ideally working with EHR or clinical data.
Proficiency in Python, SQL, bash and Git
Strong analytical skills with the ability to interpret and present data effectively.
Familiarity with AWS, GCP, Azure, or other cloud computing providers (AWS preferred); experience with dbt, or similar transformation tools, is a plus.
Working knowledge of HIPAA and PHI-handling requirements, with experience implementing data privacy, security, and integrity controls in a healthcare or clinical data environment.
Candidate must be able to function as an individual contributor with minimal direct oversight.
A passion for understanding complex issues with a data driven approach, experimenting and iterating on different ways to solve a problem.
Originally posted on Himalayas
