Senior Data Scientist

County of Los Angeles•Los Angeles, CA

About The Position

LA Health Services is seeking a Senior Data Scientist to support its integrated healthcare system serving communities across Los Angeles County. Under general supervision, this role leads the development and application of methods to identify, collect, process, organize, and analyze structured and unstructured data using advanced statistical prediction, inference, and optimization. The Senior Data Scientist communicates findings to County, departmental, and divisional decision makers and provides ongoing support to strengthen data-driven program design and management. The position develops analytical products for clinical operations, capacity planning, quality measurement, patient outcomes, patient experience, and financial sustainability. It works with partners to define complex projects, translate analyses into actionable recommendations, support implementation, and maintain data and model accuracy. The role may provide technical oversight, training, and assistance to Data Scientists and Predictive Data Analysts, but the posting defines lead capacity as technical leadership without supervision. The position is subject to shifts that may include evenings, nights, weekends, and holidays. Physical Class II – Light describes occasional lifting up to 10 pounds, some bending, stooping, or squatting, and potentially considerable ambulation. A valid California Class C Driver License or ability to use alternative transportation when needed for essential job functions is required.

Requirements

Option I: Two years of experience carrying out complex data science projects, including independently developing and applying methods to identify, collect, process, structure, and analyze data using statistical prediction, inference, and optimization to support data-driven program design and management, at a level equivalent to Los Angeles County Data Scientist.
Option II: A bachelor’s degree from an accredited college or university in an applied research field such as Data Science, Machine Learning, Mathematics, Statistics, Business Analytics, Psychology, or Public Health, including 12 semester or 18 quarter units in data science, predictive analytics, quantitative research methods, or statistical analysis, and six years of experience applying and overseeing machine learning, predictive analytics, data management, and hypothesis-driven data analysis to make actionable recommendations for program, policy, and operational decisions. At least two years must be in a lead capacity.
For Option II, a master’s or doctoral degree from an accredited college or university in an applied research field such as Data Science, Machine Learning, Mathematics, Statistics, Business Analytics, Psychology, or Public Health may substitute for up to two years of experience.
Lead capacity means assigning, coordinating, and reviewing work, ensuring proper work methods, and providing technical assistance and training; it does not involve supervision.
A valid California Class C Driver License or the ability to use an alternative method of transportation when needed to carry out job-related essential functions.
Required degree, coursework, license, or certificates must be documented with acceptable official materials as specified in the posting. International degrees require evaluation for equivalency to U.S. standards.

Nice To Haves

For applicants qualifying under Option I: additional years of experience beyond the requirement.
For applicants qualifying under Option II: experience beyond the required two years in a lead capacity applying and overseeing machine learning, predictive analytics, data management, and hypothesis-driven data analysis to make actionable recommendations for program, policy, and operational decisions.

Responsibilities

Develop and maintain inpatient bed utilization and staffing forecast models and scenario-planning tools for capacity planning and operational decisions.
Develop clinical-note natural language processing and machine-learning anomaly detection to identify trends and potential coding gaps affecting data quality, KPIs, and quality measures.
Collaborate with division, departmental, and countywide partners to define and manage complex data science projects from conception through implementation, producing actionable insights and recommendations and providing consultation during implementation.
Conduct and coordinate statistical inference and communicate findings through writing, presentations, visualizations, and interactive tools for technical and nontechnical audiences, partners, and the public.
Provide technical oversight to small teams of Data Scientists and Predictive Data Analysts as needed.
Recommend improvements to methods and algorithms, including improvements that incorporate new information.
Create and monitor automated-detection systems and provide project performance metrics that demonstrate improvements over time and iterations.
Lead discovery with departmental partners to document business requirements and frame problems for appropriate data science techniques and products.
Maintain expertise in statistical programming languages, packages, and software tools; provide training and support to data science colleagues; and ensure the quality of team code and programming logic.
Work with program staff to interpret analyses and ensure findings support data-driven program, policy, and operational decisions.
Develop and maintain operational and service-line KPI dashboards covering clinical operations, quality and patient outcomes, patient experience, and financial sustainability.
Collaborate with subject matter experts to identify and select relevant internal, external, structured, and unstructured data sources, and guide other department data experts in selecting and transforming sources.
Maintain version-controlled notebooks, model cards, technical documentation, and reproducible workflows in the Azure data environment.
Coordinate with functional teams to develop and implement products, services, tools, or business-process changes resulting from analyses.
Troubleshoot deployed analytical solutions and implement corrective enhancements to maintain data and model accuracy.
Support implementation of recommended business-process changes while maintaining analytical fidelity and accounting for operational realities; consult as changes and programs evolve, including recommending adjustments to goals and metrics.
Track project activities, milestones, and blockers through Jira and established sprint cycles.
Work with Information Technology to support collection, integration, and retention requirements for large structured and unstructured datasets from disparate sources, and advise senior data engineers and architects on systems for the data science team.