what i’m up to
I’m a third-year PhD candidate at MIT. I build large-scale orchestrated AI and optimization workflows for complex tasks.
things i’ve done
MIT (2023–2027) — PhD candidate with Prof. Patrick Jaillet. Working on AI workflow design, RL, and large-scale optimization for open math problems, finance, and energy. Funded entrepreneur.
Stanford (2019–2023) — Honors degrees in Mathematics (B.S.) with Prof. Jonathan Luk and Philosophy (B.A.) with Prof. Michael Bratman. Undergraduate Honors thesis with Prof. Yinyu Ye. Journalist at Stanford Daily.
Meta (2025–now) — Research collaboration on RL and recommendation systems.
Amazon (2025) — PhD intern, agentic store system.
things i’ve built
Open-Problem-Solver Automated prover and counterexample searcher for open math — 5 problems solved from the First Proof Challenge (Feb 2026). · [Visuals]
Cascade Hunter Automated detection of cascading proof errors in online database and traces their impact through citation dependency graphs. · [Visuals]
FundamentAI AI-orchestrated fundamental analysis for equities, including a dedicated pharmaceutical drug-level pipeline. [Visuals / General] · [Visuals / Pharma] · [Dashboard]
places i’ve spoken
Shanghai Jiao Tong University (2025) | Berkeley Simons Institute (2023) | INFORMS Annual Meeting (2024, 2025) | INFORMS Optimization Society (2026) | INFORMS Applied Probability Society (2025)
what i think about
Optimization and Control of Dynamic Topology of LLM Workflows · coming soon
Design of Large-Scale Agentic Workflow for Fundamental Analysis · coming soon With MIT LFE
Parameter-free BlockMDP · coming soon With Meta
Certifiable Stabilization of Algorithmic Markets via External Rule Primitives · coming soon
End-to-End Learning of Correlated Operating Reserve Requirements in Security-Constrained Economic Dispatch
A Two-Layer Framework for Joint Online Configuration Selection and Admission Control
Choice-Model-Assisted Q-learning for Delayed-Feedback Revenue Management
A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear Programming