Data Scientist & ML Engineer
Building production ML systems, LLM pipelines, and MLOps infrastructure across fintech, telecom, and research.
Background & Expertise
I'm a ML Engineer & Data Scientist currently at University of Rochester, where I build production data systems, LLM pipelines, and anomaly-detection tools that deliver measurable ROI. With an MS in Data Science from Rochester Institute of Technology, I specialize in bridging the gap between experimental AI research and production-grade systems.
My experience spans fintech (RedCarpetUp YC S15), telecom (T-Mobile), and academic research (UofR). I've led teams of 4–5 engineers, owned end-to-end ML product development for 500k+ users, and built MLOps infrastructure that reduced pipeline friction across the board. I care deeply about reproducibility, observability, and shipping things that actually work in production.
I'm IEEE-published and care about the intersection of rigorous statistics and pragmatic software engineering.
Production Impact Across Organizations
Isolation Forest anomaly detection on vendor invoices, eliminating manual review overhead and saving $50K annually across university procurement.
Automated Risk Strategy Simulation Tool with RCA-inclusive alerts, cutting policy deviation investigation time by 75% and boosting team productivity by 40%.
End-to-end XGBoost credit risk platform — from 5TB feature engineering to Docker + Flask production deployment — serving 500K+ users with 40% MoM growth.
Full-Stack Data Science & MLOps
Open to ML Engineering & Data Science Roles