Senior Principal Data Scientist - Remote

UnitedHealth Group•San Diego, CA

10h•$134,600 - $230,800•Remote

About The Position

This is a senior AI leadership role focused on advancing Clinical Documentation Improvement and coding intelligence solutions through state-of-the-art machine learning and generative AI technologies. The ideal candidate brings deep expertise across traditional ML, deep learning, LLMs, RAG, and agentic systems, coupled with a proven ability to translate research into scalable healthcare products. Success in this position requires solid technical leadership, stakeholder influence, healthcare data experience, and the ability to drive measurable business and model performance improvements in a highly regulated environment. 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

6+ years of experience applying machine learning, AI, and advanced analytics techniques, including experience developing and deploying production-grade AI/ML solutions
Experience working with large, complex datasets and building scalable data science solutions
Solid experience with LLM/GenAI techniques, including retrieval-augmented generation (RAG), prompt engineering, and agent-based workflows
Demonstrated expertise in multiple ML paradigms, including deep learning, sequence modeling, and tree-based methods, with hands-on experience across diverse model architectures
Solid Python programming expertise and experience with modern ML frameworks (e.g., PyTorch, TensorFlow)
Proven track record of driving measurable improvements in model accuracy, business outcomes, or product capabilities in high-stakes environments
Demonstrated solid collaboration and communication skills, with experience working directly with business stakeholders, customers, and cross-functional teams

Nice To Haves

Experience in healthcare, clinical data, or coding intelligence (ICD, CPT, SNOMED) domains
Experience leading or influencing AI strategy across large programs or portfolios
Experience working in regulated environments with data privacy, compliance, and security considerations
Experience collaborating with geographically distributed teams, including onshore/offshore delivery models
Working knowledge of SQL and data querying techniques
Familiarity with clinical documentation improvement (CDI) workflows and healthcare revenue cycle processes
Demonstrated ability to drive innovation in ambiguous, high-risk, and high-impact environments

Responsibilities

Lead the design, development, and deployment of advanced AI/ML solutions to identify and drive clinical documentation improvement (CDI) opportunities across large-scale healthcare datasets
Research, prototype, and productionize state-of-the-art AI approaches, including sequence models, Mamba architectures, CNNs, gradient boosting (e.g., XGBoost), and emerging LLM/GenAI techniques (RAG, prompt optimization, agent-based systems)
Partner closely with product, engineering, clinical SMEs, and AI research teams to translate innovative AI approaches into scalable, production-ready solutions
Serve as a technical leader and subject matter expert, guiding architecture decisions, model strategy, and experimentation frameworks to achieve step-change improvements in model accuracy and performance
Drive model evaluation, benchmarking, and continuous improvement practices to meet stringent customer expectations and contractual performance commitments
Collaborate with onshore stakeholders and customers, including participation in onsite engagements, to align AI solutions with real-world clinical workflows and business needs
Navigate complex data environments with regulatory and offshore constraints, ensuring compliant, secure, and effective use of healthcare data
Influence AI strategy and roadmap for key initiatives (e.g., OIO, CDI Reimagined, Chart Intelligence), while proactively assessing competitive and third-party technology risks
Uphold responsible AI practices by embedding fairness, transparency, and accountability into model development and deployment lifecycles
Mentor and elevate other data scientists, fostering a culture of technical excellence, innovation, and continuous learning