Senior Health Data Engineer (Evidence Generation) - Viz.ai

Viz.ai is the leader in building and deploying AI-powered Care Pathways, trusted by 2,000 hospitals across the United States and ranked the #1 Healthcare AI Platform by hospitals and health systems.

The Evidence Generation team ensures rigorous real-world data demonstrates how Viz.ai’s platform improves patient outcomes, provider efficiency, and health system performance. This role focuses on building the data foundation for evidence generation by designing automated pipelines that transform raw, messy EHR data into clean, audit-ready research datasets.

Role Overview

Viz.ai’s AI-powered care coordination platform accelerates patient treatment by coordinating care teams. Your mission is to create the data infrastructure that validates the platform’s impact through real-world evidence. You’ll solve complex data-mapping challenges, ensuring accuracy from ingestion to data lock, with results directly impacting patient care.

Key Responsibilities:

Health Data Engineering & Automated Pipelines

• Design and maintain version-controlled Python/SQL pipelines to transform raw EHR extracts (FHIR bundles, HL7v2 messages, flat files) into structured, EDC-ready datasets, handling field mapping, unit harmonization, deduplication, and complex derivation logic.

• Reconcile disparate data models, adapting to site-specific EHR variability, mapping constraints, and schema changes.

• Apply LLM and NLP techniques to extract structured clinical variables from unstructured sources (clinical notes, pathology/radiology reports, discharge summaries) and validate their accuracy.

Clinical Data Management (CDM) & Quality Control

• Drive end-to-end data management for Evidence Generation studies, including ingestion, cleaning, quality control (QC), and data lock.

• Implement programmatic QC workflows for automated anomaly detection, field mapping validation, query generation, and audit trail checks to reduce manual review burden.

• Build and maintain data dictionaries, EDC forms, and eCRF specifications for standardized ingestion and downstream analytics.

• Ensure inspection-ready documentation with strict data provenance and compliance throughout the dataset lifecycle.

Site Strategy, Governance, & Enablement

• Partner with site IT/informatics and internal teams to navigate EHR system constraints and translate complex site data realities into feasible study data capture plans.

• Author and maintain foundational clinical governance documents, including Data Management Plans (DMPs), SOPs, runbooks, and transformation/mapping specifications.

• Guide internal teams on process optimization and best practices for interacting with real-world health datasets across varying care pathways.

• Collaborate closely with Israel-based engineering and AI teams to align technical operations and pipeline development.

You Will Thrive in This Role If:

• You enjoy working with raw, complex EHR data and take satisfaction in engineering clean, structured, study-ready datasets.

• You are strong in Python and SQL, passionate about building automated, reproducible ETL pipelines, and eager to leverage modern LLM/NLP tools for structured data extraction.

• You value clinical rigor and compliance, remaining meticulous about data integrity, audit trails, and maintainable documentation standards (e.g., DMPs and SOPs).

• You excel at technical problem-solving, adept at navigating complex field-mapping challenges while balancing immediate study timelines with long-term pipeline scalability.

• You are a collaborative communicator, skilled at translating technical EHR/data pipeline realities into clear, actionable insights for diverse stakeholders.

Qualifications:

Required

• 5+ years in clinical research, real-world evidence (RWE), or health informatics.

• Proven ownership of research database builds, including cleaning, QC, and data lock.

• Strong SQL and Python skills for building automated ETL pipelines, transformations, and programmatic QC checks.

• Hands-on experience transforming raw EHR extracts (FHIR, HL7v2, or flat-file exports) into structured, EDC-ready datasets.

• Familiarity with clinical terminologies (e.g., ICD-10, CPT, LOINC, RxNorm) and standard health data structures.

• Experience handling data model variations across different health systems.

• Experience writing and maintaining governance collateral, including DMPs, SOPs, runbooks, and mapping specifications.

• Working knowledge of version control (e.g., Git) and reproducible-pipeline practices.

• Familiarity with LLM/NLP tools for extracting structured variables from unstructured clinical text.

• Familiarity with regulated-data requirements (GCP, 21 CFR Part 11, HIPAA).

Preferred

• Hands-on experience with major EDC platforms (e.g., REDCap, Castor, Veeva).

• Familiarity with standardized health and clinical trial data models (e.g., OMOP CDM, CDISC SDTM/ADaM, PCORnet).

• Understanding of FHIR resource structure and EHR data exports.

What Success Looks Like:

• First 30 days: Understand EHR data sources, active studies, and current data management processes; meet key stakeholders.

• By 60 days: Standardized database templates are in use, data dictionaries and eCRFs are built/updated, and an SDV/QA approach is documented.

• By 90 days: A raw-EHR-to-EDC pipeline is built and validated for at least one care pathway, with clear audit trails and reproducible outputs.

Why Join Viz.ai?

• Make an impact by improving patient outcomes and provider efficiency.

Be part of an amazing team where collaboration and innovation drive success.

• Work in a remote-first or hybrid environment with flexible schedules.