Eric Grynspan

New York, NY
Data Engineer — Healthcare AI & Fintech

I design and build production-grade data pipelines — from ingestion and transformation to orchestration and AI enrichment. Current focus: revenue cycle management, FHIR R4 claims analytics, and LLM-based clinical document enrichment with structured validation layers. Production standards throughout: tested, monitored, and documented.

Stack
Python SQL Snowflake dbt Dagster Airflow AWS Terraform FHIR R4 RCM LLM Enrichment Docker
Projects
Denied Live
FHIR R4 → Snowflake → dbt → Dagster. 495K claims · 51.9% denial rate · $1.2M+ recoverable. CARC-based denial root-cause classification, RCM work queue separation, and T2D+CKD real-world evidence cohort.
Trust but Verify Live
LLM enrichment + dual-validation governance across 226 patient records. LLM-as-Judge blind review, structured rules engine across 6 clinical categories, confidence scoring, and Gold/Review routing.
Own the Model, Own the Returns Live
Alpha Vantage + SEC EDGAR + FRED → S3 → Athena → Power BI. +92% risk-adjusted return premium for AI-native builders vs. integrators. Spearman ρ = +0.800, p ≈ 0.005.
LinkedIn GitHub dbt Docs