Data/ML Engineer building production data pipelines in Finance and Banking for KeyBank on the Finance Data Team where my work includes Pipeline development and testing, CI/CD, and stakeholder engagement.

🎓 Currently: Finishing an M.S. in Data Science at the University of Pittsburgh (expected 2027) 🔧 Building: A dbt + Postgres data warehouse for job market analytics (star schema, CDC, Type-2 SCD)

akoya-pcf-pipeline Production pipeline processing spatial proteomics imaging data (Akoya PhenoCycler Fusion) end-to-end — ingestion, illumination correction, cell segmentation (Cellpose), feature extraction, phenotyping (Scanpy/Leiden/UMAP), and spatial analysis (Squidpy). Containerized with Docker, GitHub Actions CI/CD, and HPC/Slurm deployment. Python Docker Cellpose Scanpy Squidpy HPC

lab-accession-app Desktop application that replaced a 47-sheet shared Excel accession log with a real SQLite-backed system. Packaged and cross-platform (Windows/Mac) via PyInstaller and GitHub Actions CI/CD; demoed to lab staff with positive feedback. Python CustomTkinter SQLite PyInstaller

job_market_analyzer Data pipeline analyzing job market trends — currently being rebuilt into a proper star-schema warehouse (fact/dimension tables, dbt snapshots for Type-2 SCD, CDC) on Supabase Postgres. Python dbt PostgreSQL ETL

Languages: Python, SQL Data Engineering: dataform, terraform, dbt, Snowflake, ETL/ELT pipeline design, SQLite, PostgreSQL, BigQuery ML / Analysis: scikit-learn, statsmodels, Scanpy, Squidpy, Cellpose Infrastructure: Docker, GitHub Actions (CI/CD), HPC/Slurm Domain: Finance and Banking, Healthcare data, HIPAA-compliant systems, clinical databases AI Tools: Antigravity, ClaudeCode, Copilot

LinkedIn · Cleveland, OH