Hello, I'm
PhD Candidate at MIT
Center for Transportation & Logistics | Deep Knowledge Lab
I enhance global supply chain performance by leveraging AI, optimization, and advanced analytics to transform procurement, logistics, and energy systems. Currently exploring how agentic AI technologies can revolutionize supplier intelligence and transportation.
MIT Center for Transportation & Logistics — Deep Knowledge Lab
I'm a PhD candidate at MIT's Center for Transportation & Logistics, where I develop and deploy machine learning and operations research solutions that connect forecasting with decision models to drive efficiency, resilience, and sustainability in global supply chains.
My research sits at the intersection of artificial intelligence and supply chain optimization. I believe we're at the cusp of an amazing transformation in supply chain research and the overall global economy—and I'm committed to being at the forefront of that change.
Before MIT, I held leadership and analytics roles at Amazon (Tokyo), Flock Freight, Zillow, and Arrive Logistics, where I developed pricing strategies, implemented ML systems, and led operations teams. My time as a site leader at Amazon Japan (Tokyo) gave me invaluable cross-cultural leadership experience and a deep appreciation for operational excellence.
As a PhD Researcher at MIT's Center for Transportation and Logistics (Deep Knowledge Lab), I focus on developing AI-driven solutions for procurement, supplier intelligence, and logistics optimization.
Building agentic AI systems that enable procurement-focused agents to retrieve, reconcile, and synthesize evidence from RFx documents, supplier master data, and contract repositories distributed across heterogeneous data silos and database types.
Designing end-to-end workflows for supplier intelligence, including document understanding and structured extraction, retrieval over multi-format artifacts, and tool-using agents that generate auditable outputs for sourcing, compliance checks, and contract term comparisons.
Developing reinforcement learning and dynamic programming methodologies for operational decision problems, including optimal routing in maritime and over-the-road settings under realistic constraints (capacity, service times, and cost structures).
Integrating machine learning forecasting with optimization models for logistics networks, including demand prediction in volatile environments and dynamic pricing for freight services.
15th International Conference on Ambient Systems, Networks and Technologies (ANT), Procedia Computer Science, Elsevier
April 2024
Supply Chain Management Review Magazine
June 25, 2025
IEEE
September 2025
Annals of Operations Research
December 2025 (Under Review)
MIT DSpace
May 2024
SCALE Expo, MIT
January 2024
7th Interdisciplinary Conference on Production, Logistics and Traffic, Darmstadt, Germany
March 2025
IEEE High Performance Extreme Computing Conference
September 2025
MIT CTL Agentic AI Roundtable
December 2025
MIT CTL Summer School
July 2025
MIT Center for Transportation & Logistics
Spring 2026
A selection of conferences, roundtables, and academic events where I've presented my research and engaged with industry and academic leaders.
I'm always interested in discussing research collaborations, industry partnerships, or opportunities to advance supply chain innovation.
MIT Center for Transportation & Logistics
Deep Knowledge Lab
Cambridge, MA