Senior Data & AI Engineer
Core
Design and deliver data engineering and clinical NLP pipelines to transform structured and unstructured EMR data into standardized clinical data for transplant-focused research and operations.
Role type
Senior hands-on IC data & AI engineer (clinical NLP)
Builds
Production data pipelines, ETL workflows, and OMOP CDM mappings for transplant oncology
Domain
Healthcare / Biomedical Informatics / Clinical NLP
Deliverable
production ML models
Required skills
Clinical NLP, OMOP CDM, Python, SQL, ETL orchestration, HL7 FHIR, entity recognition, normalization (ICD/SNOMED/RxNorm/LOINC), LLMs, deep learning, data quality validation
Preferred skills
Biomedical informatics, clinical domain knowledge, mentorship
Technologies
Python, pandas, SQL, OMOP, OHDSI, HL7 FHIR, HL7 v2, LLMs, deep learning frameworks
Responsibilities
Design, implement, test, deploy, and maintain pipelines integrating structured EMR data and processing unstructured clinical narratives; Develop entity and relationship extraction workflows for diagnoses, symptoms, labs, medications, and procedures; Normalize structured source codes and extracted clinical concepts using standard terminologies; Implement clinical context interpretation (negation, uncertainty, temporality); Build and evaluate hybrid approaches using rules, dictionaries, statistical models, and LLMs; Partner with clinicians to define schemas and translate requirements into engineering specs; Measure performance and conduct clinical error analysis; Build ETL workflows, APIs, and validation controls for OMOP CDM; Document architecture and mentor engineers.
Seniority
Senior, hands-on IC
