OverviewLocation: Remote, U.S.-based
Type: Full-time technical role
The RoleKaroo Health is seeking a Data Scientist to bridge the gap between complex healthcare data and actionable clinical and business insights. In this role, you will lead the development of predictive models and advanced analytics that drive our value-based care mission. You will be a key part of our multidisciplinary team, working closely with Data Engineering, Product, and Clinical teams to build the "brain" of the Karoo platform.
A successful Data Scientist must be a curious problem solver who thrives in the "build" phase of a startup. You are equally comfortable writing production-grade code as you are explaining a complex model's output to a clinical or business stakeholder.
What You'll Do- Predictive Modeling & Risk Stratification: Develop and deploy machine learning models to identify high-risk, high-cost members before they require expensive acute services (e.g., ER visits or inpatient stays).
- Clinical Intelligence: Complete research on claims and EHR data to identify opportunities for new clinical interventions to reduce risk of adverse events.
- Value-Based Care Analytics: Lead the analysis of total cost of care (TCoC), utilization, and patient attribution to measure performance against baseline contracts.
- Data Quality & Validation: Implement rigorous validation techniques to ensure model accuracy, fairness, and consistency, particularly when dealing with "noisy" clinical and claims data.
- Cross Collaboration: Work with Engineering and Analytics team members to provide modeling insights to be surfaced in applications and BI reports.
- Safeguard Data: Ensure strict compliance with healthcare data regulations (e.g., HIPAA, HITRUST) and implement data security best practices.
What We're Looking For- Education: Bachelor's or Master's degree in Data Science, Statistics, Computer Science, or a related quantitative field.
- Experience: Minimum 5 years of professional experience in an advanced analysis or Data Science role.
- Healthcare Domain: Experience with payer claims files and other healthcare data formats (e.g., FHIR, HL7).
- Technical Proficiency: Expert level Python/R and SQL skills.
- Modeling Expertise: Proven track record of building and deploying production-grade ML models (e.g., regression, classification, clustering, neural networks, etc).
- Regulatory Knowledge: Familiarity with HIPAA and HITRUST compliance requirements for managing sensitive patient data.
- Communication: Exceptional ability to translate complex technical findings into clear narratives for executive and clinical audiences.
- Must be legally authorized to work in the United States and not require employer sponsorship now or in the future
Why Join Us- Competitive salary and equity in an early-stage startup.
- Opportunity to define the technical solution from the ground up
- Fully remote work environment with flexible hours
- A collaborative and transparent company culture that values creativity and ownership
