About Alignment Health
Alignment Health is committed to serving seniors and the chronically ill and frail. They aim to transform conventional healthcare by putting seniors first. The company fosters growth and innovation within a team passionate about improving and saving lives.
About the Role
The Data Scientist will blend deep analytical expertise with production-grade software development skills to construct reliable, scalable solutions on Alignment Health's proprietary clinical intelligence platform. This role involves owning initiatives from problem framing to model delivery and collaborating with software and data engineering partners for production deployment. The ideal candidate will be a mission-driven Data Scientist focused on enhancing risk score accuracy, CMS audit preparedness (RADV), and developing AI-powered tools for clinical documentation review and integrity. This position plays a crucial part in advancing AVA, the proprietary clinical intelligence platform, by developing next-generation models for autonomous chart review and NLP/GenAI-driven documentation analytics, operating at the intersection of healthcare, compliance, and machine learning.
Job Duties/Responsibilities
- Own end-to-end solutions: translate ambiguous healthcare and operational problems into AI/ML models that deliver measurable impact by selecting methods, building data/models, deploying services, instrumenting observability, and real-world feedback loops.
- Partner with Product, Engineering, and Clinical leaders to embed data science into workflows like claims processing, utilization management, provider network optimization, risk adjustment, etc.
- Deliver clinical intelligence features such as autonomous chart review, disease detection, compliance forecasting, and quality analytics.
- Build AI/NLP/LLM models for document understanding and information extraction, including OCR, NER, and vision models.
- Advance quality and payment integrity: create models and automated QA to reduce manual review, increase accuracy, and surface documentation anomalies and audit risk.
- Champion engineering excellence: internal libraries, reusable components, coding standards, code reviews, and clear documentation.
- Own the lifecycle: monitoring, drift detection, alerting, and post-deployment reviews.
Requirements
Experience
- 2-5 years delivering production-grade data science or ML software with measurable impact.
- Strong software engineering fundamentals: data structures, algorithms, modular design, API design, documentation.
- Proficiency in Python plus SQL; experience building reusable packages, utilities, and CLI tools.
- Applied knowledge of ML (tree ensembles, boosting, NLP/LLMs, deep learning) and experimental design.
- Experience with high-volume, high-dimensional, and unstructured data; strong data quality mindset.
- Experience with Git workflows, code reviews, CI/CD.
- Excellent data visualization and storytelling skills.
- Ability to thrive in ambiguous, fast-paced environments.
Preferred Qualifications
- Healthcare domain experience; familiarity with CMS/Medicare Advantage operations.
- Document understanding systems with OCR/NER and LLM pipelines.
- Experience with NoSQL and performance optimization.
- Contributions to internal frameworks or open-source; published work.
Education
- Required: Bachelor’s degree in Computer Science, Data Engineering or similar technical field.
- Preferred: MSc/PhD in CS, Engineering, Math, Statistics, or related field.
Specialized Skills
- Python, SQL
- Databricks (Spark, Delta Lake)
- MLflow, Unity Catalog, Git, CI/CD, Docker
- REST/GraphQL APIs, orchestration
- NLP/LLM & Vision: OCR, NER, embeddings
- Ability to communicate positively, professionally and effectively with others; provide leadership, teach and collaborate with others.
- Effective written and oral communication skills; ability to establish and maintain a constructive relationship with diverse members, management, employees and vendors.