Data Scientist 2

Role

Optum seeks a Data Scientist 2 to build and deploy applied machine learning solutions that address complex clinical and business problems using large-scale healthcare data. The role involves end-to-end ownership of modeling work, from problem framing and feature engineering to deployment and post-production monitoring, with an emphasis on interpretability, regulatory compliance, and production-quality code.

Key Responsibilities

• Participate in design, development, and deployment of applied ML solutions for healthcare.
• Drive end-to-end model lifecycle: problem framing, feature engineering, model development, evaluation, validation, explainability, deployment, and monitoring.
• Develop and review production-grade Python code following software engineering best practices (testing, modularization, version control, CI/CD).
• Architect scalable data science workflows using Python, SQL, and distributed data processing frameworks in cloud or enterprise environments.
• Apply classical ML, deep learning, time-series modeling, and survival analysis techniques as appropriate.
• Ensure models are interpretable, explainable, and meet enterprise governance, regulatory, and ethical standards (bias, fairness, auditability).
• Partner with engineering, product, clinical, and business stakeholders to translate ambiguous problems into actionable analytical solutions.
• Review and approve modeling approaches and influence architectural and methodological decisions.
• Communicate insights, risks, and tradeoffs to technical and executive audiences.

Requirements

• 4+ years building production-quality, maintainable, and testable code.
• 4+ years with machine learning and statistical modeling fundamentals, including feature engineering, model training/tuning/evaluation, and model interpretability/explainability (e.g., SHAP).
• 4+ years hands-on with deep learning architectures where appropriate.
• 4+ years experience with time-series analysis and survival analysis.
• 4+ years experience with vibe coding tools such as Cursor, Claude Code, and Windsurf.
• 4+ years healthcare data literacy: claims, EHR, lab, pharmacy data; coding systems (ICD, CPT, NDC, SNOMED, LOINC); interoperability standards (FHIR, HL7); reasoning about data quality, missingness, bias, and confounding.
• 4+ years contributing to complex applied data science initiatives from concept to production and working in cross-functional environments.
• Advanced proficiency in Python for data science and ML (Pandas, NumPy, scikit-learn, PyTorch or equivalent).
• Advanced SQL skills for complex data transformations and analytical workflows.

Preferred Qualifications

• Experience with MLOps practices (deployment, monitoring, retraining, drift detection).
• Prior experience in regulated or highly governed environments.
• Familiarity with cloud platforms and distributed computing (e.g., Spark, Databricks, AWS, GCP, Azure).

Soft Skills

• Excellent written and verbal communication; able to convey technical concepts to non-technical stakeholders.
• Ability to balance model sophistication, interpretability, scalability, and business impact.

Location & Telecommute

• Role allows telecommuting from anywhere within the United States; telecommuters must adhere to UnitedHealth Group’s Telecommuter Policy.

Compensation & Benefits

• Salary range: $72,800 to $130,000 annually (full-time basis).
• Benefits include a comprehensive benefits package, incentive and recognition programs, equity stock purchase, 401(k) contribution, and career development opportunities.