Join Optum, a global leader dedicated to improving health outcomes through innovative technology. As a Lead Data Scientist, you will shape the future of healthcare claims payment integrity, driving impactful strategies and delivering advanced data science solutions within the Databricks Lakehouse environment. This role offers a unique opportunity to contribute to a culture of inclusion and collaboration, working alongside talented peers and advancing health optimization on a global scale.

Our team focuses on critical areas like claims processing, payment accuracy, and issue resolution. You'll leverage cutting-edge technologies like PySpark, MLflow, and Delta Lake to tackle complex challenges and make a tangible difference in the lives of millions. Embrace a career where you can truly make an impact by Caring, Connecting, and Growing together.

Lead the end-to-end data science strategy and execution for key Payment Integrity use cases, including leakage detection, adjudication accuracy, and contract issue resolution.

Develop and oversee advanced modeling approaches, feature engineering strategies, and impact measurement frameworks.

Mentor senior and junior data scientists, foster collaboration with AI/ML Engineering for seamless productionization, and establish best practices for data quality, governance, and explainability within a Databricks environment.

Drive feature store adoption, create reusable model assets, and embed explainability techniques like SHAP and bias checks. Lead A/B tests and quasi-experimental designs to validate findings and demonstrate ROI.

Translate complex insights into measurable business outcomes, such as recovery dollars and prevented leakage. Ensure code quality through reviews, establish reproducibility standards using MLflow, and optimize performance at Spark scale.

Collaborate effectively with domain experts, finance, audit, and engineering teams to transition prototypes into robust production solutions. Guide story slicing, estimation, and backlog health within Agile frameworks.

A Bachelor's degree or equivalent practical experience is required, complemented by over 8 years of progressive experience in Data Science, with at least 3 years dedicated to leading data science initiatives.

Possess deep expertise in model governance, monitoring, and data quality practices, particularly within Protected Health Information (PHI) compliant settings. Proficiency in Databricks technologies, including PySpark, Spark MLlib/scikit-learn, MLflow, and Delta Lake, is essential.

Demonstrate a strong foundation in statistics and machine learning techniques, such as sampling, leakage control, class imbalance handling, time series analysis, and anomaly detection. Excellent stakeholder communication and influencing skills are critical for driving decision-making.

Preferred qualifications include a Master's degree and exposure to healthcare domains such as Call Centers, Provider Revenue Cycle Management (RCM), and Electronic Health Records (EHR)/clinical data. Experience with fraud, waste, and abuse analytics, graph methods, causal inference, pricing/actuarial analysis, Feature Store design, and model serving patterns will be highly advantageous.