As a Senior Machine Learning Engineer, you will focus on the design and implementation of high-performance predictive models using structured and semi-structured healthcare data. You will bridge the gap between statistical research and production-grade software, turning raw clinical and claims data into actionable predictions that improve patient outcomes and operational efficiency.
Key Responsibilities:
• Model Development: Design, train, and optimize classical ML models (Classification, Regression, Clustering, Time-Series) for healthcare use cases. • Feature Engineering: Architect and maintain advanced feature pipelines and feature stores to ensure the most relevant signals are extracted from complex claims data. • End-to-End Deployment: Manage the full ML lifecycle, from exploratory data analysis (EDA) and hyperparameter tuning to deploying models as high-availability microservices. • Software Engineering: Write robust, production-ready Python code, ensuring that ML components integrate seamlessly with our core healthcare platforms. • Performance & Validation: Conduct rigorous statistical validation of models to ensure accuracy, fairness, and the absence of bias, particularly in clinical decision-support tools. • On-Call & MLOps: Participate in an on-call rotation to support production pipelines. Advance CI/CD frameworks specifically for ML (Model CI), ensuring seamless retraining and redeployment. • Compliance: Lead audits and ensure all ML workflows strictly adhere to HIPAA and Inovalon's internal data governance policies.
Qualifications:
Experience: Minimum 8 years of total experience, with 4+ years focused on building and deploying classical ML models in a production environment.
Technical Stack:
• Proficiency in Python and standard ML libraries (e.g., scikit-learn, XGBoost, LightGBM, Statsmodels). • Deep Statistical Knowledge: Strong understanding of statistical significance, hypothesis testing, and model interpretability (e.g., SHAP, LIME). • Data Tools: Experience with SQL and Big Data technologies (e.g., Spark/PySpark, Hadoop) for processing large-scale tabular datasets. • Cloud & MLOps: Proficiency with AWS/GCP/Azure and containerization (Docker, Kubernetes). Experience with workflow orchestration like Airflow or Prefect. • Architecture: Proven track record with Feature Stores and automated model monitoring/drift detection. • Domain Knowledge: Familiarity with healthcare standards (HL7, FHIR, ICD-10 codes) and HIPAA regulations is a significant plus.
Soft Skills:
• Analytical Rigor: A data-first mindset that prioritizes statistical validity over black-box approaches. • Mentorship: Experience guiding junior engineers in best practices for code reviews and experiment tracking. • Collaborative Spirit: The ability to explain complex model outputs to non-technical stakeholders (Product Managers, Clinicians).