We are seeking a Data Architect—Clinical Informatics to support projects in the National Center for Advancing Data Science and Analytics Collaboration (NacDacC) Clinical Enclaves. This individual will work closely with data scientists, stakeholders, and clinical sites to monitor, improve, and maintain data quality and phenotypes across clinical datasets, ensuring high-quality submissions. The successful candidate will also develop and maintain pipelines for ancillary data acquisition, support new enclave requests, and create disease-specific phenotypes for various NIH enclaves.

Key Responsibilities: 

• Manage and optimize data ingestion and ETL pipelines to support the integration of diverse healthcare datasets, including clinical, claims, and ancillary data from multiple sources, such as electronic medical records (EMRs) and disease registries.

• Design and develop advanced healthcare data solutions aligned with industry standards to support organizational objectives.

• Contribute to the modeling, normalization, and transformation of healthcare data.

• Collaborate with cross-functional teams to build robust data pipelines and solutions leveraging the Observational Medical Outcomes Partnership (OMOP) Common Data Model and other healthcare data standards.

• Ensure compliance with data standards and interoperability protocols (e.g., HL7 FHIR, HL7v2, and OMOP) to harmonize and link disparate data sources.

• Develop and maintain data quality scorecards and pipelines for clinical and ancillary datasets.

• Provide subject matter expertise in healthcare standards (e.g., SNOMED, LOINC, RxNorm) and interoperability frameworks to advance data acquisition and linkage strategies.

• Collaborate with internal teams to iterate on data quality improvements and implement scorecards to monitor ongoing performance.

Qualifications:

• Master’s degree in Clinical Informatics, Health Informatics, Data Science, or a related field or equivalent experience.

• Proven experience in data quality management, clinical data pipelines, and phenotype development.

• Strong skills related to SQL, Python, R, and Jupyter Notebook; experience with cloud computing platforms and using version control systems (e.g., Git) and collaborative development tools.

• Demonstrated expertise in healthcare knowledge standards, controlled terminologies (e.g. SNOMED, LOINC, RxNorm, etc),standard data models (e.g. OMOP, HL7 FHIR, STDM, etc.) and healthcare interoperability standards; HL7 FHIR, HL7v2, X12, NCPDP, CCD-A, CCD, etc.

• Strong problem-solving skills and attention to detail.

• Ability to work collaboratively with multidisciplinary teams and stakeholders across various NIH Institutes.

Nice to Have:

• Experience with patient registry (cancer, renal, etc…) data.

• Familiarity with NIH data and processes

• Knowledge of clinical practice and research. An understanding of operating procedures and workflows within a hospital or ambulatory setting.

• General knowledge of Artificial Intelligence (AI) components and techniques.