Designs and develops of scalable solutions using AI tools and machine-learning models
Performs research and testing to develop machine learning algorithms and predictive models
Utilizes big data computation and storage tools to create prototypes and datasets
Conducts model training and evaluation
Integrates, tests, tunes, and monitors solutions
Critically evaluate valuation processes to identify gaps or invalid assumptions
Independently design and implement mathematically rigorous methodologies for measuring program efficacy
Extract and manipulate large-scale healthcare data (claims, clinical, SDoH) to build independent, scalable valuation and predictive models
Act as a strategic communicator, translating complex methodologies and financial impacts into compelling narratives for non-technical executive stakeholders
Develop operational frameworks to translate clinical interventions into defensible financial forecasts and enterprise-wide statements
Navigate extreme ambiguity to scope undefined business problems and transform raw data into production-ready valuation frameworks without an existing playbook
Analyzes use cases of ML algorithms and apply findings to enable business decisions by deriving insights through data visualization
Writing complex SQL and Python/R code to extract data from a variety of databases and data sources
Conduct exploratory data analysis from complex data sources and build key data sets to support company mission operational analysis
Builds complex ML/AI models using common methods within R and Python
Analyzes the ML algorithms that could be used to solve a given problem and rank them by their success probability
Develop logging, alerting, and mitigation strategies for handling model errors
Evaluate and design experiments to monitor key model metrics and identify improvement opportunities
Produces fairness review for each developed model, to ensure model is free of bias
Set up continuous integration/continuous deployment (CI/CD) pipelines used for model automation
Model deployment with containers such as Kubernetes and/or Docker
Produce clean code that has been properly unit tested and optimized for performance
Completes proper deployment integration testing to ensure seamless deployment
Performs other duties as assigned
Requirements
A Bachelor's degree in a quantitative field (e.g., statistics, mathematics, economics, engineering, computer science) required or equivalent experience
Master's or PhD preferred
Requires 5–7 years of progressively complex data science experience, with a proven track record of delivering high-impact solutions in healthcare or regulated environments
5+ years Intermediate knowledge & experience with SQL required
5+ years experience in developing Machine learning/AI/Predictive Models in R or Python required
5+ years Intermediate knowledge of Git required
Experience using DataBricks platform preferred
Experience in VBC data science, including shared savings models, risk adjustment, or clinical efficacy evaluation preferred
Background in high-stakes environments translating complex data architecture and statistical results into executive-level strategy preferred
Tech Stack
Docker
Kubernetes
Python
SQL
Benefits
health insurance
401K and stock purchase plans
tuition reimbursement
paid time off plus holidays
flexible approach to work with remote, hybrid, field or office work schedules