Principal Data Scientist

Central Health•Austin, TX

4d•Hybrid

About The Position

The Principal Data Scientist is a senior leader and technical authority responsible for advancing Central Health System’s data science capabilities in support of population health, care management, and organizational decisionmaking. Operating under the general guidance of the VP of Data Insights & Innovation, this role leads and manages the organization’s Data Science team while serving as the primary data science authority within the organization, providing expert guidance on scientific rigor, validity, and equity of analytical and AI solutions. Working in close partnership with the Sr. Director of AI & Digital Innovation, the Principal Data Scientist provides critical technical input to the AI governance process, including risk assessments, model validation, efficacy adjudication, and alignment with frameworks such as the NIST AI Risk Management Framework (AI RMF). This role also establishes and enforces data science standards governing data quality, feature engineering, model documentation, and analytical reproducibility, ensuring that all data assets and methodologies used in AI and advanced analytics meet the organization's scientific and regulatory expectations. While the Sr. Director leads overall AI strategy, implementation and deployment, this role ensures that the underlying data science is sound, reproducible, ethical, and clinically meaningful. This individual will leverage the organization’s enterprise data environment, including Epic (EHR), VBA (TPA), Microsoft Azure (cloud infrastructure), Snowflake (cloud data platform), and numerous other data sources including clinical and business applications and our local health data utility (HDU formerly HIE), to develop and operationalize scalable, high-impact data science solutions. The Principal Data Scientist also serves as a senior technical advisor to Data Analyst teams, helping to oversee advanced analytics and ensuring advanced analytical deliverables meet the standards required to drive actionable insights across the organization.

Requirements

5 years of experience with applied data science, statistical modeling, or quantitative research experience post- PhD, with increasing responsibility and complexity.
3 years of experience in healthcare, public health, population health, or a similarly regulated and complex data environment.
2 years of demonstrated expertise in building, validating, and monitoring predictive models and machine learning solutions in a production or near-production environment.
3 years of experience developing models for population health, care management, risk stratification, or clinical decision support.
2 years of experience working with cloud-based data platforms such as Microsoft Azure and/or Snowflake for largescale data science workflows.
3 years of experience directly managing or leading a team of data scientists or quantitative analysts, including hiring, performance management, and professional development.

Responsibilities

Lead, manage, and develop a team of data scientists, providing day-to-day supervision, performance management, coaching, and professional growth planning.
Set clear team goals, priorities, and performance expectations aligned with organizational objectives, and hold team members accountable for quality, timeliness, and scientific rigor.
Recruit, onboard, and retain top data science talent, building a high-performing team with complementary skills across modeling, analytics, and MLOps.
Foster a collaborative, inclusive, and psychologically safe team culture that encourages innovation, intellectual curiosity, and continuous improvement.
Serve as the organization’s foremost technical expert in applied data science, statistical modeling, and machine learning as they relate to healthcare and population health.
Establish and maintain data science standards, methodologies, and best practices for model development, validation, documentation, and lifecycle management across the team.
Provide technical mentorship and direction to team members and data analysts, fostering a culture of scientific rigor and continuous learning.
Champion reproducible research practices, including version control of models, datasets, and analytical pipelines.
Design, develop, and maintain predictive models and forecasting solutions that directly support population health management, care coordination, and chronic disease management programs.
Build and operationalize risk stratification models to identify high-risk patients and populations for proactive intervention by clinical and care management teams.
Develop disease progression models, readmission risk models, utilization forecasting, and other advanced analytics that inform care management and resource allocation strategies.
Leverage Epic clinical and operational data, including ADT events, clinical documentation, orders, and registry data, as primary source inputs for model development and validation.
Partner with the Clinical Informatics team to guide and inform predictive modeling efforts, ensuring models are grounded in clinical workflow context, aligned with care delivery priorities, and practically implementable at the point of care.
Collaborate with clinical, population health, and care management stakeholders to translate operational needs into well-defined data science problems with measurable outcomes.
Ensure all models are validated for accuracy, reliability, fairness, and clinical relevance before deployment, with ongoing monitoring for model drift and performance degradation.
Partner with the Sr. Director of AI & Digital Innovation to provide expert data science input into the organization’s AI governance processes, policies, and committee structures.
Conduct technical evaluations of AI and machine learning tools under consideration for enterprise adoption, assessing scientific validity, algorithmic bias, data quality requirements, and clinical appropriateness.
Adjudicate the efficacy of AI solutions by reviewing vendor-provided evidence, internal pilot results, and published literature to inform go/no-go recommendations.
Apply knowledge of the NIST AI Risk Management Framework (AI RMF) and related frameworks (e.g., ISO/IEC 42001) to assess and document AI risk relative to organizational tolerance and regulatory requirements.
Identify and communicate potential risks associated with AI models, including bias, data drift, explainability gaps, and failure modes, ensuring the Sr. Director and governance committees have the scientific context needed for informed decision-making.
Support the development and maintenance of model documentation, including model cards, data lineage, and fairness assessments, ensuring transparency and auditability.
Leverage deep data science expertise to actively contribute to the design and development of AI solutions, translating governance insights, model evaluation findings, and clinical data patterns into actionable recommendations that shape how AI tools are built, refined, and validated for use across the organization.
Lead the design and execution of advanced analytics projects, including predictive modeling, machine learning, natural language processing (NLP) for clinical text, and time-series forecasting.
Apply sophisticated statistical methods, including survival analysis, mixed-effects models, Bayesian approaches, and ensemble methods, to complex healthcare data environments.
Develop forecasting models to support operational planning, including patient volume projections, staffing optimization, and financial performance indicators.
Ensure analyses account for the complexities of healthcare data, including missingness, selection bias, confounding, and longitudinal follow-up.
Translate analytical findings into clear, actionable insights communicated effectively to both technical and non-technical audiences.
Serve as the senior technical reviewer for advanced analytics work produced by Data Analyst teams, ensuring methodological soundness and alignment with organizational standards.
Define and maintain the boundary between standard reporting/analytics and advanced data science work, guiding appropriate escalation and consultation.
Collaborate with Data Analyst teams to build their statistical and analytical capabilities through mentorship, code reviews, and the development of reusable analytical frameworks and tools.
Contribute to the development of a shared analytics environment built on Azure and Snowflake, including reusable data pipelines, feature stores, and model deployment infrastructure, in collaboration with Data Engineering.
Partner with data governance and data engineering teams to ensure that data assets used for modeling and analytics are accurate, complete, well-documented, and governed appropriately.
Actively identify and mitigate sources of bias in data and models, ensuring that analytical and AI solutions promote health equity and do not exacerbate disparate outcomes.
Adhere to all applicable data privacy and security standards (HIPAA, etc.) in the collection, use, and storage of data for analytical purposes.
Contribute to the development of the organization’s responsible AI and ethical data use policies, ensuring scientific perspectives are well-represented.