Senior Data Scientist, Full Stack - Remote

UnitedHealth Group•Minnetonka, MN

3d•$91,700 - $163,700•Remote

About The Position

At UnitedHealthcare, we’re simplifying the health care experience, creating healthier communities and removing barriers to quality care. The work you do here impacts the lives of millions of people for the better. Come build the health care system of tomorrow, making it more responsive, affordable and optimized. Ready to make a difference? Join us to start Caring. Connecting. Growing together. Role Summary: A Senior Data Scientist (Grade 28) with a “Full Stack” skillset for EAR projects. This role is a primary hands-on contributor for building and deploying robust data pipelines, semantic layers, machine learning models, and LLM applications. It emphasizes practical engineering of AI solutions: rigorous model development, evaluation of modeling approaches, and implementing MLOps pipelines to ensure models are effectively integrated and maintained in production. You’ll enjoy the flexibility to work remotely from anywhere within the U.S. as you take on some tough challenges. For all hires in the Minneapolis or Washington, D.C. area, you will be required to work in the office a minimum of four days per week.

Requirements

5+ years of experience in data science, machine learning, data engineering, or related roles.
Solid foundation in statistical modeling and machine learning techniques.
Hands-on experience developing models and data pipelines for real-world problems and improving them based on feedback and data
Proficiency in Python and PySpark for building ML models and automating tasks.
Solid SQL skills for data extraction and manipulation
Demonstrated experience deploying and maintaining ML models and data pipelines in a production environment.
Comfort with the end-to-end MLOps lifecycle: using source control, CI/CD pipelines, and orchestration to automate model deployment.
Should understand concepts like model versioning, reproducibility, and monitoring in production
Ability to work independently on complex technical problems.
Solid troubleshooting skills to debug issues whether they stem from data quality, model behavior, or pipeline failures.
A mindset geared towards automation and efficiency, always looking for ways to streamline repetitive tasks

Nice To Haves

Experience with specific MLOps and cloud tools (e.g., Databricks MLflow for experiment tracking and model registry, GitHub Actions for CI).
Familiarity with infrastructure-as-code for deploying ML infrastructure
Familiarity with the Databricks Lakehouse platform and Spark. For example, knowing how to implement ML pipelines on Databricks, use Delta Lake for data versioning, and optimize Spark jobs for feature processing. Experience with Metric Views
Exposure to real-time or streaming data analysis. Experience deploying models that consume streaming data (e.g., streaming analytics or real-time dashboards) or working with technologies like Kafka or Spark Declarative Pipelines for live data feeds
Experience in mentoring junior data scientists or leading technical workstreams will be beneficial.
The ability to document work clearly and impart knowledge to others helps the overall team

Responsibilities

Build and support the Advocate Performance Data Platform that powers AmplifAI coaching, performance management, and workforce optimization capabilities
Develop scalable data pipelines, semantic models, and governed advocate performance metrics using Databricks, Snowflake, and enterprise data architecture
Integrate operational, quality, coaching, and learning data to create trusted, AI-ready data products and performance insights
Establish certified metric definitions, lineage, governance, and data quality controls to ensure consistent reporting and enterprise adoption
Enable near real-time delivery of advocate, supervisor, and coaching metrics that drive personalized coaching, commitment management, and performance improvement
Accelerate Consumer Operations transformation by providing a scalable, enterprise-ready foundation for AI-driven coaching, analytics, and workforce performance optimization while reducing duplicate development and reporting efforts