Why This Role Matters
As a Data Scientist at Personify Health, you build the predictive models that employers and health plans use to understand and manage the health of their member populations. Your work directly shapes cost forecasts and risk scores that drive real decisions — from how clients allocate wellness resources to how they plan for the year ahead. You'll work with large-scale healthcare data, contribute to a shared modeling codebase used across every model we ship, and learn what it takes to build ML systems that hold up in production. When a model's predictions are off, real people notice — so accuracy and rigor matter here.
What You'll Actually Do
- Build and train models: Develop supervised learning models for health cost prediction and risk classification using automated ML workflow tools
- Engineer features from claims data: Create and refine features from medical claims, pharmacy, biometric, and wellbeing data sources, contributing to the team's feature store of 7,500+ features
- Prepare and validate data: Clean, join, and transform large-scale healthcare datasets in Snowflake and Python, ensuring data quality before it enters the modeling pipeline
- Evaluate and improve model performance: Assess models using appropriate metrics, conduct analysis across client subpopulations, and communicate findings to senior team members
- Contribute to the shared codebase: Write clean, well-documented Python code that follows established patterns in the team's modeling library
- Support production model builds: Run automated training pipelines, validate outputs across client populations, and assist with model deployment and retraining cycles
- Collaborate with stakeholders: Work with product and client-facing teams to understand business requirements and translate them into modeling objectives
Education & Experience
What You Bring to Our Team
- Master's degree in Data Science, Statistics, Computer Science, Mathematics, or a related quantitative field; or Bachelor's degree with relevant internship or project experience
- 0–3 years of experience in a data science, machine learning, or analytics role (internships and academic project work count)
Technical Skills
- Python for data analysis and machine learning
- SQL for querying and transforming data in relational databases or cloud data warehouses
- Supervised learning methods including regression, classification, tree-based models, and ensemble techniques
- Feature engineering and data preprocessing on structured/tabular datasets
- Communicating analytical findings clearly to both technical and non-technical audiences
Preferred Skills
- Experience working with healthcare data such as medical claims, pharmacy claims, eligibility records, or biometric screenings
- Familiarity with Snowflake or similar cloud data warehouses
- Exposure to Git and collaborative development workflows (e.g., GitLab, GitHub)
- Experience with or interest in MLOps practices such as automated training pipelines, model versioning, model monitoring, or feature store management
- Experience working with cloud-based compute infrastructure (e.g., AWS EC2 or similar services): Ability to provision, configure, and use cloud compute resources to run workloads, manage environments, and support data-intensive applications
