Sr. Data Scientist - Public Healthcare Fraud Detection & Linked Data Analytics

Integrity Management Services, Inc. (IntegrityM) is a woman-owned small business specializing in assisting government healthcare organizations prevent and detect fraud and abuse in their programs.

At IntegrityM, we offer a culture of opportunity, recognition, and collaboration. We thrive off of these fundamental elements that make IntegrityM a great place to work. We offer the flexibility our employees need to challenge themselves and focus on advancing their professional development and careers. Large company perks. Small company feel.

www.integritym.com

Location: Remote 
Employment Type: Part-Time, PRN (estimated 40 hours per month)
Reports To: Vice President of PI 

Overview
The Senior Data Scientist handles advanced analytics, AI/ML modeling, and large-scale data integration to lead the development of fraud detection models for federally funded public healthcare programs to include statistical research, policy, and cutting-edge technology to detect, quantify, and mitigate fraud.

Key Responsibilities

• Lead the design, development, and implementation of advanced fraud detection and risk-scoring algorithms leveraging AI, machine learning, and explainable AI techniques, with a focus on linked, cross-agency datasets.
• Architect and oversee secure data pipelines to integrate, clean, and standardize heterogeneous datasets, including federal, state, and open-source data.
• Apply deterministic and probabilistic record linkage methods within a secure environment, ensuring compliance with security protections, and statistical purposes requirements.
• Conduct literature reviews to identify and adapt fraud taxonomies, definitions, measures, and behavioral indicators for healthcare fraud.
• Collaborate closely with stakeholders and other agencies to incorporate subject matter expertise into model design.
• Develop analytical workflows for unstructured data preparation, data quality assessment, and anomaly detection across multi-source linked data.
• Deliver reproducible, open-source analytical outputs, including datasets, codebooks, algorithms, dashboards, and documentation suitable for public release.
• Translate analytical findings into actionable insights for both technical and policy audiences via reports, dashboards, and briefings.
• Provide technical leadership and mentorship to multidisciplinary project teams, ensuring adherence to agile, collaborative, and transparent project practices.

Requirements

Required Qualifications

• 10+ years of progressively responsible experience in data science, statistical modeling, and advanced analytics, with a proven record of operationalizing AI/ML solutions.
• Demonstrated expertise in fraud detection, anomaly detection, or risk scoring in healthcare, finance, or other regulated sectors.
• Significant experience integrating and linking large-scale, multi-source datasets, including restricted and unstructured data.
• Mastery of Python, R, and similar, with experience in distributed processing frameworks (e.g., Spark) and secure cloud environments.
• Strong understanding of statistical methods, supervised/unsupervised learning, and explainable AI techniques.
• Familiarity with federal data privacy, confidentiality laws, and secure data handling (HIPAA).
• Exceptional written and verbal communication skills, with the ability to produce clear, concise, and actionable deliverables for diverse stakeholders.
• Degree (Master’s or PhD) in Data Science, Statistics, Computer Science, Applied Mathematics, or related discipline.

Preferred Qualifications

• Advanced degree (Master’s or PhD) in Data Science, Statistics, Computer Science, Applied Mathematics, or related discipline.
• Experience working with Medicare, Medicaid, or other large-scale healthcare claims and provider datasets.
• Knowledge of MOU development for data sharing, especially in interagency environments.
• Prior experience with similar secure statistical research environments.
• Track record of publishing or presenting in professional or policy forums.