Dataverse​/Data Science Lead; CBP

LMI is seeking a Dataverse/Data Science
Lead join a multidisciplinary team supporting the Department of Homeland Security (DHS) Customs and Border Protection (CBP) Program Management Office (PMO). This role is ideal for engineers who are passionate about applying technical expertise to real-world national security challenges and advancing mission-critical capabilities through research, evaluation, and informed decision-making.
This position requires U.S. citizenship and the ability to obtain a CBP Background Investigation (BI) is required; active CBP BI preferred. This position requires 20% travel that may entail remote and rugged areas.

The Data Science Lead must be a hands-on technical leader who combines advanced statistical expertise, strong coding skills, and practical mission awareness. This individual will evaluate data quality, validate assumptions, select appropriate analytical methods, and tackle complex technical challenges while ensuring findings are accurate, defensible, and actionable.

The role also requires strengthening team capabilities through technical mentorship, peer review, and consistent analytical standards. The ideal candidate can communicate complex findings, uncertainty, bias, and limitations clearly to technical, operational, clinical, and executive stakeholders.

• Lead the analytical strategy for complex operational, workflow, technology, and programmatic questions, ensuring analyses are aligned with customer priorities and decision needs.
• Serve as the lead subject‑matter expert for Microsoft Dataverse data structures, data management practices, analytical use cases, and integration with reporting, automation, and data‑science solutions.
• Assess data readiness for analytical and reporting use cases, including data quality, completeness, sensitivity, lineage, authoritative sources, access considerations, and fitness for intended measures.
• Design and maintain reporting‑ready Dataverse data models, tables, relationships, transformations, validation rules, business logic, and analytical pipelines.
• Develop, review, and apply statistical models, machine‑learning methods, exploratory analyses, predictive analytics, and AI/large‑language‑model evaluations, as appropriate.
• Perform hands‑on analysis using Python, SQL, Dataverse queries, and related tools; troubleshoot complex data, integration, transformation, reporting, and modeling issues.
• Partner with program, operational, technical, evaluation, and data‑governance stakeholders to establish appropriate baselines, denominators, comparisons, outcomes, performance measures, and evidence limitations.
• Translate complex analytical findings into concise, actionable products for technical and nontechnical decision‑makers, clearly communicating uncertainty, data‑quality issues, assumptions, bias, and causal limitations.
• Lead feature definition, model selection, validation strategies, error analysis, sensitivity testing, bias and fairness assessments, and interpretation for advanced analytics and machine‑learning efforts.
• Establish analytical standards and governance practices for reproducibility, peer review, validation, documentation, version control, data‑quality checks, and transparent communication of analytical assumptions and limitations.
• Create reusable notebooks, SQL scripts, code patterns, analytical templates, Dataverse configuration standards, data dictionaries, and quality checks to improve consistency and accelerate future work.
• Coach analysts, data scientists, and technical teams on data‑management practices, analytical methods, quality assurance, peer review, and responsible use of data and AI‑enabled capabilities.
• Coordinate with data engineering, platform, application‑development, and Power…