Data Scientist

Role overview

A rapidly scaling healthcare startup that pairs individuals with expert advocates is hiring a Data Scientist to lead predictive analytics and forecasting efforts. Reporting to the VP of Data, this role focuses on building machine learning models that anticipate patient needs, optimize operations, and shape strategic decision-making across a lean and mission-driven organization. Success in the position comes from bridging advanced statistics with practical business application and ensuring models are robust, interpretable, and high-impact.

Responsibilities

- Develop and refine machine learning models to address business challenges such as predicting patient churn, estimating operational volume, or scoring advocate quality. - Own the development of time-series forecasts that guide capacity planning and resource allocation across the organization. - Design and analyze A/B tests and causal inference studies to measure the true impact of product and operational changes. - Apply advanced statistical methods to complex datasets to surface patterns and answer difficult "why" and "how" questions. - Partner with Data Engineers to productionize models, moving them from local development into a reliable production environment. - Translate complex statistical findings into clear, actionable narratives for non-technical stakeholders and leadership.

Requirements

- Strong background in statistics, probability, and mathematics, including hypothesis testing, regression analysis, and time-series forecasting. - Proficiency in Python and its data science ecosystem (pandas, scikit-learn, statsmodels, NumPy), with a commitment to writing clean, reproducible code. - Hands-on experience with time-series analysis and forecasting techniques such as ARIMA, Prophet, or exponential smoothing. - Ability to write complex SQL queries independently, including working with cloud data warehouses like Snowflake. - Awareness of data privacy principles for handling sensitive patient information, including PHI and PII best practices. - Self-starter mindset suited to an ambiguous, fast-paced environment, with willingness to take ownership and wear multiple hats. - A master's degree or PhD in Data Science, Applied Science, or a related field is preferred.

Nice to have

- Experience deploying and monitoring models in production using tools like Docker, Airflow, or MLflow. - Prior work with healthcare or insurance claims data. - Familiarity with Natural Language Processing techniques for extracting insights from unstructured text. - Experience designing matching algorithms or ranking systems for two-sided marketplaces. - Comfort reading or writing dbt models to understand data lineage.

Benefits and work setup

- Applicants must be based in the United States.