Clinical Data Engineer
Viz.ai · Remote · United States - Remote ·
COMPENSATION
$129k – $145k
Listed on the employer's job board (Ashby)
- Fully remote (US/EU)
- Python + SQL
- Clinical Data Engineering
- NLP & LLM application
- 5+ years experience
Join the Evidence Generation team at Viz.ai to engineer the data foundation for real-world health studies. You will design version-controlled pipelines that convert messy EHR extracts into clean, audit-ready datasets, ensuring rigorous quality control from ingestion to data lock. Your work directly supports proving better patient outcomes through accurate, reproducible clinical data.
What you'll do
- Design Python/SQL pipelines to transform raw EHR extracts into structured datasets
- Handle field mapping, unit harmonization, deduplication, and complex derivation logic
- Apply LLM and NLP techniques to extract variables from unstructured clinical notes
- Drive end-to-end data management including ingestion, cleaning, QC, and data lock
- Implement programmatic QC workflows for anomaly detection and audit trail checks
- Build and maintain data dictionaries, EDC forms, and eCRF specifications
- Partner with site IT teams to navigate EHR constraints and data realities
- Author governance documents such as Data Management Plans, SOPs, and runbooks
What you'll need
- 5+ years in clinical research, real-world evidence, or health informatics
- Proven ownership of research database builds, cleaning, QC, and data lock
- Strong SQL and Python skills for automated ETL pipelines and QC checks
- Experience transforming raw EHR extracts (FHIR, HL7v2) into EDC-ready datasets
- Familiarity with clinical terminologies like ICD-10, CPT, LOINC, and RxNorm
- Experience handling data model variations across different health systems
- Knowledge of version control and reproducible pipeline practices using Git
- Familiarity with LLM/NLP tools for extracting data from clinical text
- Understanding of regulated-data requirements such as GCP, 21 CFR Part 11, HIPAA
Nice to have
- Hands-on experience with major EDC platforms like REDCap, Castor, or Veeva
- Familiarity with standardized health data models such as OMOP CDM or CDISC
- Understanding of FHIR resource structure and EHR data export methods
Stack
- Python
- SQL
- FHIR
- HL7v2
- LLM
- NLP
- Git
- REDCap
- Castor
- Veeva
How you'll work
- Remote-first company for employees in the U.S. and EU
- Flexible hybrid model for the team in Tel Aviv
- Collaboration with Israel-based engineering and AI teams
What you get
- Competitive cash compensation and equity
- Medical, dental, and vision insurance (US)
- 401(k) plan (US)
- Generous vacation time (US)
- Dental insurance and performance bonuses (Israel)
- Cibus meal allowance and office meals (Israel)