Senior AI Data Scientist

This is a fully remote position, open to applicants in Alabama, +19 more states.

📋 Description

• Define ambiguous revenue-cycle challenges as manageable modeling issues and take ownership from start to finish, including claim and invoice viability scoring, denial and underpayment forecasting, revenue/ARR predictions, and prioritization of tasks from hypothesis formulation to validated, monitored outcomes in production.

• Develop and validate models with rigorous statistical methods: careful feature engineering, effective management of missing data and class imbalance, calibration, honest assessment against basic benchmarks, and a transparent approach to uncertainty.

• Create, build, and sustain the data pipelines that support these models, integrating with source collections, billing, EHR systems, and internal data repositories, while overseeing data collection, cleansing, field mapping, and payer/plan normalization, prioritizing reliability and data quality.

• Establish and manage MLOps practices, including model monitoring and drift detection (e.g., population stability), calibration and threshold selection, benchmarking against basic standards, explainability (e.g., SHAP and interpretable coefficients), experiment and version tracking, and documentation such as model cards.

• Collaborate with subject-matter experts to encode business rules and heuristic logic alongside statistical models to achieve more accurate or defensible outcomes.

• Collect and document business requirements for revenue-cycle projects, including workflows, decision points, stakeholder goals, operational constraints, success metrics, data availability, and underlying business assumptions, maintaining traceability as these requirements change.

⛳️ Requirements

• Several years of experience in building and validating models and operating them in a production environment.

• A degree in a quantitative discipline such as statistics, computer science, mathematics, or data science, or equivalent demonstrated expertise.

• A robust statistical background in experimental design, inference, evaluation of imbalanced real-world data, and the ability to discern genuine results from artifacts of measurement.

• Profound, genuine understanding of the fundamentals: train/test discipline, overfitting and regularization, data leakage, class imbalance, calibration, and a sincere approach to model evaluation.

• Proficiency in production Python (pandas, NumPy, scikit-learn; familiarity with deep-learning frameworks is a plus) and strong SQL skills, including stored procedures and performance-optimized queries on large datasets, along with comfort in using Git and reproducible workflows.

• Practical experience in MLOps: monitoring, drift detection, experiment tracking, version control, and maintaining model health in production.

• Confidence in managing the data pipeline, extending beyond model source-system integration, scheduling, and data quality controls.

🏝️ Benefits

• Medical

• Dental

• Vision

• Life insurance

• Short-term disability

• Long-term disability

• Paid holidays

• 401k

• Generous PTO policy