Senior Clinical Data & AI Engineer — NLP/OMOP (Remote)

CareDx, Inc.; United States; Remote; USD 126,000 - 187,000; Full time

Benefits offered by this job

Health and welfare benefits

Gym reimbursement program

401(k) matching

Employee Stock Purchase Plan

Pre-tax commuter benefits

Explicit benefits page linked

Job summary

CareDx, Inc. is seeking a Senior Data and AI Engineer to lead data pipelines that transform real-world EMR data into reliable, standardized clinical data. The role combines data engineering, clinical NLP, and ontology work to harmonize records for transplant-focused analytics.

You will partner with clinicians to define schemas, validate outputs, and deploy production-grade ETL and NLP solutions, while ensuring HIPAA-compliant practices and scalable data infrastructure.

Qualifications

• 7+ years in NLP, ML, or AI engineering with production delivery in healthcare.
• Strong Python and SQL skills with ETL, data modeling, validation, and testing.
• Hands-on with structured EMR data integration using HL7 FHIR or v2 APIs and data extracts.
• Experience with OMOP and OHDSI vocabularies, concepts mapping, and terminology management.

Responsibilities

• Design and own data pipelines from EMR data to structured clinical outputs.
• Develop entity/relationship extraction for diagnoses, symptoms, labs, demographics, medications, and procedures.
• Normalize clinical concepts using ICD, SNOMED CT, RxNorm, LOINC; manage mappings and versions.
• Implement clinical context interpretation (negation, temporality, experiencer) and reconcile timelines across notes.

Skills

NLP engineering

Python

SQL

Clinical data modeling

Education

Master's or Ph.D. in CS/Computational Linguistics/Biomedical Informatics

Tools

HL7 FHIR

OMOP CDM

MedSpaCy

cTAKES

Job description

CareDx, Inc. is seeking a Senior Data and AI Engineer to lead data pipelines that transform real-world EMR data into reliable, standardized clinical data. The role combines data engineering, clinical NLP, and ontology work to harmonize records for transplant-focused analytics.

You will partner with clinicians to define schemas, validate outputs, and deploy production-grade ETL and NLP solutions, while ensuring HIPAA-compliant practices and scalable data infrastructure.