I build reliable production AI systems that connect machine learning and large language models with enterprise knowledge and real-world workflows.
RAG · LLM Evaluation · Retrieval · MLOps · Cloud AI · Observability
I’m a Senior Data Scientist at Moderna working on production AI and enterprise GenAI systems. My work spans RAG and retrieval architectures, LLM evaluation, knowledge governance, cloud-based ML services, production reliability, and forecasting platforms.
My background combines software and infrastructure engineering, machine learning research, and end-to-end production ML. I’m particularly interested in building reliable AI systems that connect models with enterprise knowledge and real-world workflows, with a focus on grounded retrieval, evaluation, observability, and scalable system design.
I hold a PhD in Biomedical Data Science and Informatics and an MS in Computer Science from Clemson University.
Reliable AI systems designed for enterprise knowledge and real-world operations.
Architect and productionize enterprise RAG systems with governed retrieval, source citations, metadata-aware search, document lifecycle controls, observability, and production reliability.
Design evaluation systems that separate retrieval quality from answer-generation quality using gold and SME-reviewed datasets, retrieval metrics, citation coverage, evidence sufficiency, unsupported-answer behavior, and latency.
Own and modernize production ML workflows with traceability, observability, AWS-managed execution, CI/CD, and repeatable operating practices that reduce manual operational work.
Selected recent roles; additional experience and education are available on the Experience page.
2023–Present — Lead architecture and productionization of enterprise AI systems spanning GenAI/RAG, retrieval and evaluation, governed enterprise knowledge, cloud ML services, observability, and production reliability. I also own modernization and reliability work for production forecasting workflows and reusable ML operating patterns.
2021–2023 — Developed and productionized end-to-end machine learning solutions in AWS and helped turn applied ML concepts into deployable capabilities using repeatable MLOps practices.
2020–2021 — Built cloud-based machine learning applications and applied statistical modeling and demand forecasting to operational business problems.