SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Vi Engage deploys predictive models into healthcare operations at major health systems and health plans, driving care navigation, specialty capture, and clinical workflows. As an Applied Data Scientist, you will own 3–5 enterprise healthcare accounts end-to-end, serving as the technical expert throughout the customer lifecycle.
Your responsibilities include:
**Data Integration & Pipeline Architecture**
Own the complete data pipeline from customer systems (claims, EHR, tokens, marketing data) into Vi's platform. You will handle ingestion, mapping, quality assurance, and make judgment calls about data limitations and feasibility.
**Pilot & Study Design**
Design rigorous studies that connect model performance to measurable business outcomes customers will commit to. You will manage experimental design including power analysis, controls, confounder management, and metrics that withstand scrutiny from sophisticated internal analytics teams.
**Production Automation**
Build per-customer ML pipelines using Vi's capabilities to train, score, and deliver insights on schedule without manual intervention. You will maintain these systems through ongoing operations.
**Customer Leadership**
Be the technical authority during onboarding and operations. You will run working sessions with clinical, IT, and analytics leaders at major health systems and health plans, translating business problems into data-driven solutions. You will occasionally travel onsite to customer locations.
**Product Strategy**
Identify patterns across your accounts and synthesize them into high-leverage product requirements, accelerating future deployments.
This is a hands-on-keyboard role with direct stakeholder exposure. You will sit with customer teams to understand their KPI targets and design solutions leveraging Vi's platform capabilities. Your field insights directly shape the product roadmap.
**Requirements**
**Must-Have:**
- Demonstrated expertise in experimental design: you have designed and run studies with commercial impact and can defend your methodology to skeptical stakeholders
- Deep data science fundamentals: you can explain how models work, evaluate them honestly, and identify their limitations; you know when simpler approaches are appropriate
- Python proficiency and ML engineering capability: fluent in pandas, scikit-learn, Airflow; you ship production code that automates client deliverables
- PySpark experience: you have built distributed data and ML pipelines on Spark against large, messy datasets
- Client-facing expertise: you can independently lead working sessions with clinical, IT, and analytics leaders at major health systems or health plans; you translate between business problems and data reality; you hold the line when answers don't match expectations
- Ownership mindset: you proactively identify and resolve issues before customers escalate them
**Nice-to-Have:**
- Healthcare or life sciences domain knowledge (claims, EHR, HL7/FHIR, lab data, population health analytics)
- Experience designing and optimizing marketing and engagement campaign targeting
- AWS data infrastructure (S3, Glue, EMR, MWAA, SageMaker)
- HIPAA and healthcare compliance/data governance familiarity
- Experience scaling products from first customer deployment to repeatable operations
**What This Role Is Not**
This is an applied, production-focused role, not a research position. Success is measured by deployments that run and customer outcomes, not novelty. You will architect and write pipelines yourself—this is not a delivery or engagement management role.
