Optum is a global organization that delivers care, aided by technology to help millions of people live healthier lives. The work you do with our team will directly improve health outcomes by connecting people with the care, pharmacy benefits, data and resources they need to feel their best. Here, you will find a culture guided by inclusion, talented peers, comprehensive benefits and career development opportunities. Come make an impact on the communities we serve as you help us advance health optimization on a global scale. Join us to start Caring. Connecting. Growing together.
This role supports the Optum Real Pre-Care CPT Predictor and Digital Front Door (DFD) initiatives, which deliver AI-driven capabilities for CPT/HCPCS prediction, healthcare intent understanding, and patient navigation. citeturn1search1 The work directly supports business objectives of improving patient estimate accuracy, streamlining prior authorization workflows, and reducing downstream claim denials. citeturn1search1
You will own meaningful pieces of the model lifecycle end to end: framing the problem with stakeholders, exploring and engineering features from healthcare data, training and evaluating models, and carrying them through to a deployed, monitored production service. This is a hands-on applied science role for someone who writes solid Python, is grounded in classical machine learning, has practical exposure to deep learning and generative AI, and has seen their own work run in production rather than stop at a notebook.
Primary Responsibilities:
-
Design, build, and evaluate machine learning models for prediction and classification problems using healthcare claims, clinical, and registration data
-
Own assigned components of the model lifecycle end to end, from data exploration and feature engineering through training, evaluation, deployment, and post-production monitoring
-
Write production-quality Python for data processing, model training, and inference, following sound software engineering practices including version control, testing, and code review
-
Apply deep learning and transformer-based approaches where they outperform classical methods, and justify model selection with rigorous experimentation
-
Build and evaluate generative AI and LLM-based components, including prompting, fine-tuning, and retrieval-augmented approaches, for applicable use cases
-
Deploy models as production services or APIs in partnership with MLOps and engineering teams, and support them post-release
-
Design and run experiments with clear evaluation metrics, baselines, and validation strategy, and communicate results and trade-offs clearly to technical and non-technical audiences
-
Partner with product managers, data engineers, and business stakeholders to translate requirements into well-scoped modeling problems
-
Contribute to model documentation, responsible AI practices, and AIRB and governance readiness for production deployment
-
Scientist Responsibilities:
-
Collaborate with research, engineering, and product teams to translate cutting-edge AI advancements into production-ready capabilities
-
Uphold ethical AI principles by embedding fairness, transparency, and accountability throughout the model development lifecycle
-
Comply with the terms and conditions of the employment contract, company policies and procedures, and any and all directives (such as, but not limited to, transfer and/or re-assignment to different work locations, change in teams and/or work shifts, policies in regards to flexibility of work benefits and/or work environment, alternative work arrangements, and other decisions that may arise due to the changing business environment). The Company may adopt, vary or rescind these policies and directives in its absolute discretion and without any limitation (implied or otherwise) on its ability to do so
Required Qualifications:
-
Bachelor's, Master's, or PhD in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Statistics, or a related quantitative field
-
5+ years of applied machine learning experience building models that solve real business problems
-
Hands-on exposure to generative AI or LLMs, including prompting, fine-tuning, or embedding and retrieval-based approaches
-
Practical experience with deep learning frameworks such as PyTorch or TensorFlow
-
Demonstrated experience taking at least one model or system into production as a deployed service or API, and supporting it thereafter
-
Solid Python programming skills, including experience writing maintainable, production-grade code rather than exploratory scripts alone
-
Solid foundation in classical machine learning, including tree-based and gradient-boosted methods, with sound understanding of feature engineering, model evaluation, and validation methodology
-
Proven ability to communicate modeling decisions, assumptions, and results clearly to cross-functional partners
Preferred Qualifications:
-
Experience with healthcare data such as claims, HL7, EHR, or medical coding systems including CPT, HCPCS, or ICD
-
Experience with multilabel or large-label-space classification problems
-
Experience with MLOps tooling and practices, including experiment tracking, model registries, containerization, and CI/CD
-
Experience delivering AI/ML solutions in a regulated or compliance-sensitive environment
-
Familiarity with Azure and cloud-based AI/ML platforms
-
Exposure to model monitoring, drift detection, and retraining workflows
At UnitedHealth Group, our mission is to help people live healthier lives and make the health system work better for everyone. We believe everyone-of every race, gender, sexuality, age, location and income-deserves the opportunity to live their healthiest life. Today, however, there are still far too many barriers to good health which are disproportionately experienced by people of color, historically marginalized groups and those with lower incomes. We are committed to mitigating our impact on the environment and enabling and delivering equitable care that addresses health disparities and improves health outcomes - an enterprise priority reflected in our mission.
#NIC #NJP