Senior Data Scientist - Clearance Required Security Clearance

Position: Senior Data Scientist - Clearance Required with Security Clearance
Location: True

Overview The Senior Data Scientist will support the Defense Health Agency (DHA) Revenue Cycle Operating System ( RevOS ) initiative by designing and implementing advanced analytics, statistical models, predictive capabilities, and decision-support visualizations within a Databricks-based environment. The role will focus on transforming complex healthcare, financial, coding, claims, payment, and operational data into actionable intelligence that enables DHA to identify revenue leakage, coding and charge-capture errors, denied or stalled claims, underpayments, aged receivables, and opportunities to recover revenue.

The Senior Data Scientist will work closely with Data Engineers, Revenue Cycle SMEs, DHA stakeholders, and product leadership to develop analytics aligned to the end-to-end revenue-cycle workflow:
Scheduling → Eligibility → Registration → Authorization → Patient Care → Documentation → Coding → Charge Capture → Claims → Adjudication → Remittance → Denials → Collections / Recovery The objective is not simply to produce reports. The role will help create analytical products and Databricks-based dashboards that identify where revenue-cycle processes are failing, quantify financial impact , prioritize corrective action, and measure recovery.

LMI is a new breed of digital solutions provider dedicated to accelerating government impact with innovation and speed. Investing in technology and prototypes ahead of need, LMI brings commercial-grade platforms and mission-ready AI to federal agencies at commercial speed. Leveraging our mission-ready technology and solutions, proven expertise in federal deployment, and strategic relationships, we enhance outcomes for the government efficiently and effectively.

With a focus on agility and collaboration, LMI serves the defense, space, healthcare, and energy sectors, helping agencies navigate complexity and outpace change. Headquartered in Tysons, Virginia, LMI is committed to delivering impactful results that strengthen missions and drive lasting value. Responsibilities
* Design and develop advanced analytics within Databricks using Python, SQL, Spark/ PySpark , statistical methods, and machine-learning techniques.
* Develop Databricks visualizations, Databricks SQL dashboards, AI/BI dashboards, and related native visualization capabilities to provide operational and executive visibility into RevOS performance.
* Create interactive dashboards supporting DHA J-8, DHN, MTF, revenue-cycle, coding, financial, and executive users.
* Translate analytical models into intuitive visualizations showing financial exposure, recovery opportunity, trends, root causes, outliers, and recommended operational priorities.
* Develop command-level RevOS SITREP dashboards using Healthy / At Risk / Critical indicators across the Front, Middle, and Back Office revenue cycle.
* Develop drill-down analytics from enterprise and DHN levels through MTF, department, provider, encounter, claim, and claim-line levels.
* Design and develop analytical models that identify and quantify potential revenue leakage and recovery opportunities .
* Analyze encounter, documentation, coding, charge, claim, denial, adjudication, payment, and accounts-receivable data to identify patterns associated with lost or delayed revenue.
* Develop detection logic for:
* Missing or incomplete charges
* Uncoded and delayed encounters
* Coding inconsistencies and potential coding errors
* Claims-readiness defects
* Denied and rejected claims
* Underpayments and unexplained payment variances
* Unmatched or unposted remittances
* Aged claims and receivables
* Eligibility and authorization failures
* Develop recoverability and priority-scoring models based on financial value, probability of recovery, aging, filing/appeal deadlines, and operational severity.
* Develop payer-performance and denial analytics to identify recurring payer behaviors, denial patterns, reimbursement variances, and process failures.
* Build predictive models that identify revenue-cycle failures before they result in lost revenue or excessive Days-to-Bill.
* Establish baselines and anomaly-detection methodologies across Front Office,…