Senior Data & AI EngineerBrisbane, CA
CareDx, Inc. · Brisbane, CA, United States ·
COMPENSATION
€•• – ••k
Listed on WeAreDevelopers
- Senior level role
- Clinical NLP focus
- OMOP CDM expertise
- Python and SQL
- Fully remote (US)
You will design and maintain data engineering and NLP pipelines that convert structured and unstructured electronic medical records into reliable clinical data. The work centers on harmonizing EMR data with the OMOP Common Data Model, specifically for transplant-focused research and operations.
What you'll do
- Design and deploy pipelines for structured EMR data and unstructured clinical narratives
- Develop workflows for entity and relationship extraction from medical notes
- Normalize clinical concepts using standards like SNOMED CT, RxNorm, and LOINC
- Implement context interpretation for negation, uncertainty, and temporality
- Build hybrid approaches using rules, dictionaries, and LLMs for extraction
- Partner with clinicians to define data schemas and annotation guidelines
- Validate OMOP data conformance and manage terminology versioning
- Document architecture and mentor junior engineers on best practices
What you'll need
- Master's or Ph.D. in Computer Science, Data Science, or related field
- 7+ years experience in NLP, machine learning, or applied AI engineering
- 3+ years developing clinical NLP solutions with real-world EHR data
- Advanced proficiency in Python, SQL, and pandas for data processing
- Hands-on experience with HL7 FHIR, HL7 v2, and API integrations
- Deep knowledge of OMOP Common Data Model and OHDSI vocabularies
- Experience with medspaCy, scispaCy, cTAKES, or similar frameworks
- Strong understanding of medical terminology and clinical workflows
Nice to have
- Experience with transplant clinical data and research outcomes
- Familiarity with OHDSI tools like Usagi, Achilles, or Data Quality Dashboard
- Background in fine-tuning biomedical language models
- Experience with OCR and document layout processing for scanned records
Stack
- Python
- SQL
- PyTorch
- TensorFlow
- Hugging Face Transformers
- medspaCy
- scispaCy
- cTAKES
- HL7 FHIR
- OMOP CDM
How you'll work
- Fully remote position
- Based in Brisbane, CA