Ascension LLC is seeking a Data Scientist (Primary) to support government-led fraud analytics efforts focused on detecting, preventing, and mitigating identity theft and financial fraud. This role serves as a core contributor to the development, testing, deployment, and monitoring of predictive models, fraud detection rules, and analytical frameworks across both production and non-production environments.

The ideal candidate is a technically strong, detail-oriented problem solver who thrives in fast-paced, ambiguous environments and can translate complex data into actionable insights. This individual will play a central role in identifying fraud patterns, enhancing model performance, and supporting rapid analytical response to emerging fraud schemes. The candidate should be self-driven, highly analytical, and capable of balancing multiple priorities while maintaining accuracy and accountability.

This role supports mission-critical analytics that directly impact taxpayer protection strategies and national financial integrity. The Data Scientist will work closely with cross-functional teams including engineers, analysts, and government stakeholders to continuously improve fraud detection capabilities.

Key Tools & Technologies: Python, R, SQL, SAS, machine learning frameworks, data visualization tools (e.g., Tableau, Power BI), big data platforms (e.g., Hadoop/Spark), cloud environments (AWS/Azure), version control tools.

Day-to-Day Activities

• Develop predictive models, classification algorithms, and anomaly detection techniques to identify fraud patterns
• Engineer and select features from structured and unstructured datasets to improve model accuracy
• Test, validate, and tune models using statistical techniques and performance metrics
• Monitor model performance, drift, and degradation across filing and non-filing periods
• Analyze fraud schemes, filing behaviors, and emerging threats to inform model updates
• Support rapid-response analytics for newly identified fraud vulnerabilities or schemes
• Collaborate with data engineers to operationalize models in production environments
• Evaluate internal and external data sources to enhance fraud detection capabilities
• Generate analytical reports, dashboards, and visualizations for stakeholders
• Document methodologies, assumptions, and model logic for transparency and auditability
• Participate in pilot analytics initiatives and support transition to production
• Contribute to continuous improvement of analytical frameworks, rules, and filters