Clinical Registry Intelligence
Built clinical ETL and NLP systems at Carta Healthcare, normalizing heterogeneous data into HL7/FHIR-aligned workflows and integrating LLM-assisted extraction into registry operations.
Selected work shaped by rigor and practical outcomes.
A focused set of projects across machine learning, healthcare, scientific reasoning, and technical education.
Flagship Work
Teaching ML Like Production
Built a rigorous mentoring and review practice at TripleTen, guiding learners through end-to-end ML systems with emphasis on evaluation, failure analysis, and production-minded decisions.
Selected Projects
RAG Systems That Hold Up
Designed PDF-based retrieval systems with careful chunking, grounding, evaluation, and failure analysis so answers stayed useful beyond the demo stage.
ML Evaluation Workbench
Built structured evaluation workflows for model comparison, validation rigor, and error analysis so ML decisions were driven by evidence rather than surface-level metrics.