Data Scientist

CAREER DESCRIPTION

DATA SCIENTIST

In addition to performance-based merit increases, this position is scheduled to receive salary range increases on the following dates:

Effective June 27, 2025 – 4.00% increase

Salary may be negotiable within the range listed above, based on position requirements and successful candidate's qualifications, subject to appropriate authorization.

This position is open to the public for a minimum of five (5) business days and will remain open on a continuous basis until 11:59 p.m. (PST) on the day the County's needs are met.

OPEN TO THE PUBLIC

This recruitment will establish an open eligible list. This list will be used to fill current and future Data Scientist vacancies within the Health Care Agency. This eligible list may also be used to fill positions in similar and/or lower classifications.

The first round of consideration will be Thursday, May 22, 2025.

HEALTH CARE AGENCY

The County of Orange, Health Care Agency (HCA) is a dynamic organization dedicated to creating and supporting an environment that promotes the achievement of optimal individual, family and community health. Under the direction of the Agency Director, a new and dynamic executive team with an organizational structure comprised of five (5) service areas - Correctional Health, Administrative Services, Behavioral Health Services, Public Health Services, and Specialized Medical Services is committed to meeting the health needs of the diverse Orange County community.

THE DEPARTMENT

The Behavioral Health Services (BHS) Division consists of the following service areas: Adult and Older Adult Behavioral Health, Children and Youth Services, Quality Management Services, Data Analytics and Evaluation, Crisis and Acute Care Services, Substance Use Services, and Forensics and Justice Involved. These service areas provide a culturally competent and client-centered system of behavioral health services for all eligible county residents in need of treatment for alcohol and other drug abuse and mental health care.

THE PROGRAMS

Data Analytics and Evaluation is responsible for the end-to-end development of complex data projects designed to enhance clinical decision-making, precision health, performance measurement, and financial and resource forecasting in the areas of mental health and substance use. This often begins with mapping complex business workflow designs and identifying opportunities for improved data collection, analysis and/or business operations. Data science/analytics staff perform data engineering, predictive analytics/modeling, machine learning, large language models, data visualization and other techniques to draw insights from data, and evaluation staff leverage these insights to assist programs with identifying innovative and effective ways to improve client care.

THE OPPORTUNITY

The Data Scientist positions are situated within BHS and will coordinate, contribute to and maintain data products needed to support the integrated behavioral health plan. Data Scientists will work collaboratively with both technical and nontechnical partners to execute large-scale or complex projects in response to identified business needs and may lead teams as part of a large-scale project. Some positions may supervise non-Data Scientist staff.

Some examples of duties and responsibilities include but are not limited to:

Collaborates with division, departmental and countywide stakeholders to solicit, define and manage complex data science projects from conception through implementation/deployment.

Possesses and maintains a high level of expertise in programming languages/packages and other software tools (i.e., SQL, R, Python, etc.).

Uses different machine learning techniques on complex business problems, with an understanding of algorithm types, feature selection, variable importance, hyperparameter tuning and optimization.

Conducts end-to-end predictive modeling that includes data preprocessing, feature engineering, model development, training and selection, deployment and monitoring of the model in production environments, and visualization of findings.

Ensures that code is well-documented, reproducible and follows best practices to facilitate knowledge sharing and collaboration within the team.

Ensures that projects result in actionable insights and recommendations that can be used to support business decisions and allocation of resources.

Conveys findings and communicates effectively with a wide range of audiences, including technical and nontechnical staff, stakeholders and members of the public.

Provides peer review regarding selection and improvement of data science tools and ensures that the team’s tools and systems are well documented.

Provides training and support to other staff as necessary.

DESIRABLE QUALIFICATIONS & CORE COMPETENCIES

The ideal candidate will possess at least three (3) years of cumulative experience using Python, PySpark, R and/or SQL; working with XML or JSON files; and/or working in Azure Databricks. Additionally, the ideal candidate will possess at least two (2) years of experience in one (1) or more of the following data science methods: data engineering, machine learning, natural language processing, deep learning/neural networks and/or predictive analytics.

Experience working with FHIR, HL7 and/or USCDI standards; using/integrating with GitHub; and familiarity with ICD-10-CM, CPT, HCPCS, CDT, SNOMED CT, NDC and/or LOINC medical terminology standards is preferred, but not required.

Additionally, the ideal candidate will demonstrate extensive knowledge and/or experience in the following competencies:

Professional and Technical Expertise

Understanding of one or more scripting/programming languages, particularly Python and/or R

Understanding of ETL workflows

Possessing domain expertise in one or more of the following: financial modeling, revenue cycle management, health disparities, behavioral health conditions

Conducting end-to-end data science projects that include exploratory data analysis, feature engineering, model selection, deployment of models into production environments and visualization of findings

Proficiency with SQL and enterprise-class cloud-based databases

Applying current techniques for the prediction of rare event outcomes

Developing natural language processing models

Understanding of population health risk stratification

Processing healthcare claims data files (X12 837 and 835) and revenue cycle management

Developing/maintaining data dictionaries and related metadata and contributes to internal knowledge repositories

Assisting with troubleshooting and root cause analysis on application function problems

Providing peer review regarding selection and improvement of data science tools and ensures that the team’s tools and systems are well documented

Leading Cross-Divisional Collaboration Project Management

Collaborating with Information Technology (IT) staff to support collection, integration, and retention requirements for large sets of structured and unstructured data from disparate sources

Acting as a resource for IT staff in the selection and design of systems for use by the data science team

Leading the discovery process with stakeholders to document business requirements and frame business problems and/or processes so that appropriate corresponding data science techniques and products can be identified and deployed

Understanding and applying Agile development methodologies

Assigning and monitoring the work of a project team to accomplish project goals and objectives

Mentoring and providing technical assistance to project team members

Evaluating, updating, creating and/or maintaining processes and procedures

Professional Impact Building & Maintaining Relationships

Collaborating with division, departmental and countywide stakeholders to manage highly complex projects

Creating rapport and working with department staff/vendors to identify and address business initiatives

Encouraging open and productive communication

Writing Oral Communication

Communicating technical and complex information in a clear and concise manner

Communicating findings and conclusions effectively to a wide range of audiences, including technical and nontechnical staff, stakeholders, community partners and members of the public

Listening effectively and presenting ideas and complex materials clearly, concisely, logically and persuasively, both orally and in writing

MINIMUM QUALIFICATIONS

Click here to learn more about the minimum qualifications for the Data Scientist classification, as well as the Physical, Mental and Environmental Conditions.

RECRUITMENT PROCESS:

Human Resource Services (HRS) screens all applications to identify the qualified applicants for the position based on the skills required to meet the needs of the County. After the initial screening, the qualified applicants will be referred to the next step and notified of all further procedures applicable to their status in the competition.

Application Screening (Refer/Non-Refer): Applications and supplemental responses will be screened for qualifications that are highly desirable and most needed to successfully perform the duties of this job. Only those applications exhibiting qualifications as listed in the job bulletin will be referred to the next step.

Online Assessment (Weighted 100%)

Candidates who closely match the ideal candidate profile based on the bulletin requirements will be invited to participate in an online assessment. Candidates will be notified of their test date and access code, if applicable. The most successful candidates will be placed on an eligible list.

Based on the Department's needs, the selection procedure listed above may be modified. All candidates will be notified of any changes in the selection procedure.

Eligible List

Once the assessment has been completed, HRS will establish an eligible list of candidates. Candidates placed on the eligible list may be referred to a selection interview to be considered for present and future vacancies.

Veterans Employment Preference

The County is committed to providing a mechanism to give preferential consideration in the employment process to veterans and their eligible spouses and will provide eligible participants the opportunity to receive interviews in the selection process for employment and paid internship openings. Please click here to review the policy.

ADDITIONAL INFORMATION

EMAIL NOTIFICATION:

Email is the primary form of notification during the recruitment process. Please ensure your correct email address is included in our application and use only one email account.

NOTE: User accounts are established for one person only and should not be shared with another person. Multiple applications with multiple users may jeopardize your status in the recruitment process for any positions for which you apply.

Candidates will be notified regarding their status as the recruitment proceeds via email through the GovernmentJobs.com site. Please check your email folders, including spam/junk folders, and/or accept emails ending with "governmentjobs.com" and "ocgov.com." If your email address should change, please update your profile at

FREQUENTLY ASKED QUESTIONS:

Click here for additional Frequently Asked Questions.

For specific information pertaining to this recruitment, please contact Laura Katsis at or by phone at