Clinical Data Scientist

Viz.ai is the leader in building and deploying AI-powered Care Pathways and helping doctors do their work. The Viz Platform is deployed in 2,000 hospitals across the United States and trusted by many of the leading life sciences companies. The platform uniquely combines real-time, multimodal clinical data with deep clinician engagement to detect disease earlier, coordinate care teams, and help ensure patients receive the right treatment faster. Viz.ai was the first company to be awarded CMS reimbursement for AI and is ranked the #1 Healthcare AI Platform by hospitals and health systems in the Black Book Research survey. For more information, visit Viz.ai.

This is not a traditional eCRF-only Data Manager role. We are hiring a data-science-capable leader who can build and run research databases, operationalize EHR→EDC automation — including hands-on transformation of raw EHR data pulls into EDC-ready, analysis-ready datasets — and own data quality through data lock, while performing light-to-moderate statistical analysis as needed. This position plays a critical role in driving Viz's Evidence Generation strategy by managing the full data life-cycle for clinical research and quality improvement studies, from raw source extraction through database build, cleaning, transformation, and downstream analysis. This role requires expertise in creating sophisticated data management systems, building and running ETL/data transformation pipelines against raw EHR extracts, performing statistical analyses, automating data integrations, and ensuring robust data integrity practices.

1. Configure/maintain EDC forms and eCRF specifications as needed to support ingestion and downstream analysis, focusing on scalability and standardization.

2. Own end-to-end Data Management for Evidence Generation studies: build, validate, and maintain research databases from ingest → cleaning → QC → data lock.

3. Develop and run data cleaning workflows (queries, reconciliation, audit trails), and ensure inspection-ready documentation.

• Pull, parse, and profile EHR datapulls (e.g., FHIR bundles, HL7v2 messages, flat-file/CSV extracts) directly from site or enterprise data sources.

• Design and build transformation pipelines (Python/SQL) that clean, standardize, and reshape raw EHR extracts into structured, validated, EDC-ready datasets — including field mapping, unit harmonization, deduplication, and derivation logic.

• Establish repeatable, version-controlled transformation code (not one-off scripts) so pipelines can be re-run reliably as new EHR extracts arrive across sites and studies.

• Design and operate data model strategy for automated ingestion of EHR-level RWE into the EDC.

• Work hands-on with APIs/integration endpoints and unify disparate data models (site/EHR variability, mapping logic, versioning, schema evolution).

• Partner with site IT/informatics and the Product team to understand EHR constraints, extract structures, and change management.

• Translate EHR data realities into feasible study data capture and monitoring plans.

• Create and maintain DMPs, SAPs, SOPs, runbooks, transformation/mapping specs, and training materials that operationalize the above processes across care pathways.

• Perform statistical analyses on cleaned, transformed datasets (descriptive, comparative, time-to-event where appropriate) and support evidence packages and reporting.

• Apply data science techniques (feature/cohort derivation, exploratory data analysis, data quality scoring) to raw EHR-derived datasets to accelerate study readiness and reduce manual review burden.

• You possess advanced analytical capabilities, enjoy solving complex data problems, and have a deep interest in clinical research methodologies and outcomes.

• You enjoy getting hands-on with messy, raw EHR extracts and take satisfaction in turning them into clean, structured, analysis-ready datasets.

• You are proficient in developing automated and scalable data solutions, and possess strong coding and database management skills (e.g., SQL, SAS, Python, R).

• You excel in strategic thinking and operational execution, adept at balancing immediate data management needs with long-term data infrastructure goals.

• You are highly organized, methodical, and meticulous about data integrity, compliance, and documentation standards.

• You enjoy collaborating with diverse stakeholders, effectively translating complex statistical concepts into actionable insights that drive clinical research forward.

• 5–7+ years in clinical research/RWE data management with hands-on database build + cleaning/QC ownership.

• SQL + Python (or R) for data transformation, ETL pipeline development, QC checks, and reproducible pipelines.

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

• Experience with EHR or EHR-derived datasets and understanding of common structures/coding systems (ICD-10, CPT, LOINC, RxNorm preferred).

• Practical familiarity with API-based ingestion and integrating multiple data sources/models.

• Experience building/owning DMPs/SOPs/runbooks and maintaining audit-ready documentation.

• Working knowledge of version control and reproducible-pipeline practices (e.g., Git) to keep transformation code auditable.

• Familiarity with integrating leading AI techniques into your work product.

• Experience with EDC platforms (Medidata Rave, REDCap, Castor, Veeva, etc.).

• CDISC familiarity (SDTM/ADaM) or strong equivalent standardization experience.

• Stats experience in real-world/implementation studies (propensity methods, time-to-event, mixed models) — not required to be a PhD biostatistician.

• Experience with pipeline orchestration/data engineering tooling and cloud (AWS) data warehouses.

• You are energized by building scalable, audit-ready Evidence Generation data systems; turning raw EHR-derived real-world data into clean, analysis-ready research datasets with minimal manual effort.

• You take end-to-end ownership of Research Databases (ingest → validation → cleaning → QC → data lock), and you continuously improve the EHR→Viz→EDC auto-import pipeline by designing resilient mappings, unifying disparate data models, and proactively troubleshooting data issues with sites and internal partners.

• You communicate clearly, document rigorously, and train teammates through lightweight SOPs, runbooks, and templates so the work scales across multiple care pathways.

• You manage competing priorities well and deliver on-time, high-quality outputs that support study milestones and sponsor expectations, while consistently practicing Viz core values.

• After 90 days: there is visible improvement in data management execution — standardized database templates are in use, an agreed SDV/QA approach is documented, a first raw-EHR-to-EDC transformation pipeline is built and validated for at least one care pathway, automated import performance is measured and improving, and stakeholders see faster turnaround on monitoring/cleaning and sponsor-ready reporting (with clear audit trails and reproducible outputs).

• If you are looking to make an impact, we are mission-driven and are making a difference in peoples’ lives every day.

• If you want to be a part of an amazing team , our people are the heart of everything we do.

• If you are a self-starter and naturally motivated, our work is driven by curiosity, innovation and team collaboration which allows us to leverage our skills immeasurably.

We are a remote-first company across the U.S. and EU, with a team in Tel Aviv operating in a flexible hybrid model, conveniently located near a train line.
Viz.ai is committed to providing highly competitive cash compensation, equity, and benefits. The compensation offered for this role will be based on multiple factors such as location, the role’s scope and complexity, and the candidate’s experience and expertise, and may vary from the range provided.
In the U.S., Viz offers competitive benefits, including medical, dental, vision, 401(k), generous vacation, and additional benefits to full-time employees. Viz.ai is an Equal Opportunity Employer and considers applicants for employment without regard to race, color, religion, sex, orientation, national origin, age, disability, genetics, or any other basis prohibited by federal, state, or local law.
Employees in Israel are offered a comprehensive benefits package, including, among others: dental insurance, performance-based bonuses, a Cibus meal allowance, meals at the office, and more.
If you’re applying for a position in San Francisco, please review the San Francisco Fair Chance Ordinance guidelines applicable in your area.

#LI: GH1

#LI: remote