Healthcare ML and scoring workflows
Built and supported production risk-scoring and future-cost workflows for large-scale claims and clinical data. Work included validation notebooks, run tracking, operational handoffs, and reliability improvements.
AI/ML Engineer
Building production ML systems, healthcare data workflows, and practical AI engineering tools.
I work across machine learning platforms, Databricks, PySpark, MLflow, data quality, model validation, and AI observability. My focus is turning model and data workflows into reliable systems that teams can run, debug, and improve.
Experience
Platform-minded ML engineering
MLOps and model lifecycle systems
Developed platform capabilities for ML pipelines, lineage, data quality, experiment tracking, model versioning, and reproducible model operations using Python, Databricks, PySpark, Delta Lake, and MLflow.
Optimization and migration
Improved Spark-heavy preprocessing and inference workflows through profiling, caching, broadcast joins, query refactoring, cluster tuning, and migration from older orchestration patterns to Databricks Workflows.
Document AI and applied ML
Earlier work included medical text extraction, NLP, model serving, deep learning workflows, and product engineering for healthcare document intelligence systems.
Selected work
Public-safe project themes
ML platform and lifecycle tooling
Platform work for tracking, validating, versioning, and operating ML workflows across data science and engineering teams.
Python / Databricks / MLflow / PySparkHealthcare data pipeline modernization
Migration and optimization work for analytics workflows, replacing brittle configuration and storage patterns with more maintainable execution and Delta-based handoffs.
Databricks Workflows / Delta Lake / Spark SQLAI observability and context engineering
Exploration of observability, evaluation, and structured context workflows for more reliable AI-assisted development and model monitoring practices.
Arize / OpenTelemetry concepts / Codex workflowsContact