Remote Senior Clinical Data & AI Engineer

CareDx, Inc.; Brisbane (CA); On-site; USD 145,000 - 187,000; Full time

Benefits offered by this job

Health benefits

Gym reimbursement

Living Donor Policy

Job summary

CareDx, Inc. in Brisbane, California, is seeking a Senior Data and AI Engineer to own end-to-end data pipelines that convert structured EMR data and unstructured clinical notes into reliable, standardized clinical data for transplant-focused analytics.

You will design NLP workflows, apply OMOP CDM, leverage ICD/SNOMED/RxNorm vocabularies, and collaborate with clinicians to deploy production-grade solutions while ensuring security and compliance.

Qualifications

• 7+ years in NLP/ML/AI engineering, with production delivery.
• 3+ years developing clinical NLP solutions using real-world EHR notes.
• Strong experience with Python, SQL, data modeling, and ETL.
• Hands-on with HL7 FHIR, HL7 v2, APIs, or DB extracts.
• Experience with OMOP CDM and OHDSI vocabularies.
• Proven ability to lead technical work and communicate with clinicians.

Responsibilities

• Own design, implementation, testing, deployment, and maintenance of data pipelines.
• Develop entity and relationship extraction workflows for diagnoses, symptoms, labs, demographics, meds, allergies, procedures.
• Normalize clinical concepts using ICD, SNOMED CT, RxNorm, LOINC; manage terminology mappings.
• Implement clinical context interpretation: negation, temporality, experiencer, and status.
• Build production APIs/services and monitor data quality and model performance.
• Document architectures, review code, mentor engineers, and ensure HIPAA-aligned practices.

Skills

Python programming

SQL

Clinical NLP

Transformer models

Clincal terminology

Education

Master’s or Ph.D. in CS/Computational Linguistics/Bioinformatics

Tools

medspaCy

scispaCy

cTAKES

OHDSI/OMOP

PyTorch

TensorFlow

Hugging Face Transformers

Job description

CareDx, Inc. in Brisbane, California, is seeking a Senior Data and AI Engineer to own end-to-end data pipelines that convert structured EMR data and unstructured clinical notes into reliable, standardized clinical data for transplant-focused analytics.

You will design NLP workflows, apply OMOP CDM, leverage ICD/SNOMED/RxNorm vocabularies, and collaborate with clinicians to deploy production-grade solutions while ensuring security and compliance.