Principal Engineer, Data Insights

EnableComp earned its reputation in the toughest corners of the revenue cycle by solving the complex claims no one else could. We developed Complex Revenue Intelligence™ (CRI), a smarter approach to predict and prevent revenue loss. Powered by the e360 RCM® AI-driven platform and the most expansive complex revenue cycle data set, today EnableComp helps more than 1,000 hospitals nationwide recover $3 billion annually from complex claims, denials, and revenue recovery. By cutting through complexity, we help hospitals thrive, resulting in recognition as Black Book’s #1 Specialty RCM provider for complex claims and revenue integrity in 2024 and 2025, a multi-year Top Workplaces honoree, and a SOC 2 Type II and HITRUST e1-certified platform.Our Vision is to empower healthcare providers to focus on patient care, not revenue cycle complexity. Our Mission is to uncover what others miss—turning every client dollar recovered into insight that helps prevent future loss. We live our Core Values of Uncompromising Integrity, Ecstatic Clients, and Empowered Team Members by operating with trust, accountability, and a “we before me” mindset. We pursue Innovation and Profitable Growth through continuous improvement and thoughtful problem-solving, and we believe work should include Fun—celebrating success, recognizing our people, and maintaining healthy work-life balance.POSITION SUMMARYThe Principal Engineer, Data Insights, is responsible for leading the hands-on development of EnableComp’s predictive intelligence platform, transforming our Databricks lakehouse from data storage into a revenue-generating prediction engine. As the Principal Engineer, Data Insights, you will own ML model development for multi-dimensional work prioritization, business insights, and strategic build-vs-partner decisions that determine how we scale our predictive capabilities. This is a 100% hands-on technical leadership role where you will architect and build the platform before scaling a team.JOB RESPONSIBILITIESReal-time ML scoring infrastructure processing 10K+ claims daily with <2-second latencyFeature engineering pipelines transforming raw claims, payer contracts, fee schedules, and partner data into predictive signalsMulti-dimensional "super scoring" system combining contract variance, denial probability, and recovery likelihood across internal + partner datasetsModel deployment architecture supporting A/B testing, automated retraining, and agentic development workflowsMLflow model registry managing versioning, lineage, and deployment pipelinesUnity Catalog implementation governing model access and data lineageMedallion architecture (Bronze/Silver/Gold) for analytics-ready dataWork Prioritization & Super Scoring: Multi-dimensional scoring combining partner intelligence (denial scoring) with internal production data and learningsPortfolio Optimization: Cash flow forecasting, recovery probability modeling, capacity planningContract Intelligence: Variance detection, underpayment prediction (evaluate build vs partnership)Additional Insights: Identify and develop predictive opportunities as platform maturesDesign and personally build ML platform architecture on Databricks/Azure from the ground upDevelop production-ready predictive models from concept through deploymentImplement distributed computing optimization for processing millions of historical claimsBuild automated model monitoring, retraining triggers, and performance dashboardsLeverage agentic development frameworks for rapid model iterationOwn end-to-end ML pipeline: feature engineering, model training, production deployment, monitoringAchieve <2-second latency for real-time scoring at scaleDesign APIs enabling consumption across operations, finance, and product teamsIntegrate denial scoring intelligence into super-scoring frameworkOwn integration architecture whether building internally or partnering externallyREQUIREMENTS & QUALIFICATIONSBachelor’s or Master’s degree in Computer Science, Software Engineering, or a related field.Must have 6-8+ years deploying production ML systems, preferably in financial services or healthcare domainsDeep hands-on expertise with Databricks, MLflow, Spark optimization, and distributed computing architecturesModern ML frameworks: Python, scikit-learn, XGBoost, LightGBM, deep learning libraries.Statistical modeling: Time series forecasting, ensemble methods, feature engineering at scale, survival analysis, causal inferenceProduction deployment: Real-time scoring APIs, model monitoring, A/B testing frameworksData engineering at scale: Unity Catalog governance, Delta Lake ACID transactions, streaming ingestion, schema evolution managementComplex claims domain knowledge (VA, Workers’ Comp, MVA, Out-of-State Medicaid)Understanding of revenue cycle workflows and predictive opportunitiesHealthcare data experience: claims processing, payer behavior, denial patterns, medical codingAzure ML ecosystem and cloud infrastructureData governance and HIPAA compliance re