Senior Data Scientist

About the role

The Senior Data Scientist plays a critical role in driving evidence-based decision-making across Vibrant’s programs and operations. They are responsible for designing, developing, validating, and deploying predictive models and analytical reports that support core business and programmatic objectives.

Responsibilities

• Design, develop, validate, and deploy predictive models and analytical reports that address core business and programmatic objectives.
• Ensure models and reports are explainable, well-documented, and accompanied by clear articulation of assumptions, opportunities, and limitations.
• Monitor deployed models for data drift, performance degradation, and quality issues; lead remediation efforts as needed.
• Translate complex analytical findings into accessible insights for program staff, leadership, and external partners.
• Champion data literacy across the organization—partnering with business users to build understanding of how models and reports inform Vibrant’s work.
• Develop and deliver training materials and workshops on data literacy, analytical thinking, and model interpretation.
• Collaborate with data engineers and analytics teams to ensure data pipelines and infrastructure meet modeling and reporting needs.
• Apply statistical and machine learning methods rigorously—selecting appropriate techniques, validating assumptions, and assessing uncertainty.
• Contribute to Vibrant’s data science infrastructure, including model registries, version control, and deployment pipelines on AWS.
• Support ad hoc analytical requests from program and operational teams.

Requirements

• Strong proficiency in Python and/or R for data analysis, modeling, and reporting; familiarity with relevant libraries (scikit-learn, pandas, tidyverse, etc.).
• Hands-on experience with AWS data science services, including SageMaker for model training and deployment.
• Advanced statistical knowledge—including regression, classification, clustering, causal inference, and experimental design.
• Experience working with large, complex datasets in cloud-based data warehouse environments (Redshift, Snowflake, or similar).
• Excellent written and verbal communication skills—able to present findings clearly to technical and non-technical audiences alike.
• Strong analytical curiosity, attention to detail, and ability to work independently on ambiguous problems.
• High level of influencing ability.

Qualifications

• Bachelor’s or Master’s degree in a quantitative discipline (statistics, computer science, epidemiology, public health, applied mathematics, or related field), or equivalent applied experience.
• 4+ years of applied data science experience, including AI/ML model development and code-based analysis and reporting.
• Experience in public health, behavioral health, social services, or a mission-driven organization a strong plus.
• Prior experience as a team lead or similar helpful.
• Familiarity with equity-centered data practices and considerations for algorithmic fairness a plus.