AI Data Scientist – Indianapolis Health

Overview

Milliman’s Indianapolis Health practice is seeking a highly skilled and motivated AI Data Scientist to join our growing practice. This role is focused on applied machine learning for healthcare, enhancing and extending an existing production AI and analytics platform, and contributing new ideas and prototypes across our broader artificial intelligence (AI) and machine learning (ML) portfolio. The ideal candidate has hands-on experience with healthcare data, strong ML and statistical fundamentals, and the ability to operationalize results through dashboards. You will also contribute to applied large language model (LLM) capabilities, including prompt design and agent-style workflow automation, using disciplined evaluation, traceability, and guardrails appropriate for regulated environments.

Responsibilities

In this role, you will support:

• Production AI & Prototyping: Enhance and extend existing production AI/analytics platforms and develop new applications through research, ideation, and rapid prototyping to solve complex public sector healthcare challenges.
• Model Development & Interpretability: Develop interpretable, defensible ML models and statistical methods to support user workflows, including explainable feature attribution, comparative benchmarking, and structured model output summaries.
• Client Deliverables & Communication: Produce high-quality written reports, exhibits, and presentations that clearly communicate methods, findings, limitations, and recommended actions to non-technical audiences.
• Governed GenAI & LLMs: Engineer governed solutions including prompt design, RAG, and agentic workflow orchestration (e.g., MCP) with rigorous evaluation and traceability for regulated use.
• Operational ML Excellence: Own model performance by defining acceptance metrics, monitoring data health (including drift), tuning thresholds, and designing dashboards for triage and KPI tracking. 
• Business Development Support: Support proposals and RFPs by drafting technical approach sections, methods descriptions, solution diagrams, and participating in capability demos. 
• Cross-Functional Collaboration: Partner with domain SMEs (actuarial, clinical, pharmacy, policy) to translate requirements into quantifiable solutions, validate outcomes, and align outputs to real operational decisions. 
• Engineering Best Practices: Collaborate with data engineering to build scalable pipelines with robust quality controls, reproducibility, logging, and documentation.

Qualifications

• Consulting-Grade Communication: Demonstrated ability to write clear client-ready reports, build presentations, and explain limitations and tradeoffs to non-technical stakeholders.
• Applied ML & Statistical Rigor: Strong applied ML skills on large-scale data with interpretable methods, comparative analytics, and defensible anomaly scoring approaches suitable for regulated review and support contexts.
• End-to-End ML Delivery: Proven experience taking projects from ambiguous problem framing to maintainable deployment and adoption in operational workflows.
• Healthcare Data Expertise: Hands-on experience with healthcare data (claims/encounters preferred), including feature engineering, validation, and explainability for audit/oversight workflows.
• Applied Generative AI: Practical experience with prompt design, API-based integration, and governed retrieval (RAG) with evaluation and guardrails.
• Production Engineering: Strong Python skills in shared codebases (OOP, modular design) with modern engineering discipline (testing, code reviews, structured logging, Git/GitHub).
• Data at Scale: Strong SQL plus distributed processing (Spark, PySpark, Databricks preferred) with strong data quality and validation practices.

Required

• Bachelor’s degree in Data Science, Computer Science, Statistics, or a related field
• 5+ years of experience in data science, machine learning, or AI engineering roles

Preferred

• Master’s degree in Data Science,