Jiaming Zeng is a Research Engineer and Tech Lead specializing in long-term memory, interpretability, and evaluation infrastructure for large language models. She received her PhD from Stanford University working with Ross Shachter, Susan Athey, and Daniel Rubin. Her research focused on employing causal models and machine learning to develop interpretable models for medical decision making. While an undergrad at MIT, she worked with Cynthia Rudin to develop interpretable machine learning models for predicting prisoner recidivism.

As a technical leader, she specializes in translating cutting-edge ML research into scalable, production-grade systems. Her experience spans leading end-to-end delivery of conversational analytics and NL2SQL systems—such as self-consistency and Looker Query generation—as well as driving R&D for medical coding LLM pipelines. Today, she focuses on frontier long-context architectures, long-term memory mechanisms, inference efficiency, and rigorous automated evaluation frameworks.

Prior to her current work, she was a Postdoctoral Researcher in IBM Research’s Computational Health group, investigating algorithmic fairness, bias mitigation, and retrieval methods in clinical data. Her background also includes an AI Residency at X, the Moonshot Factory (formerly Google X) building machine learning tools for ocean conservation and sustainable fishing, as well as an AI Research internship on NVIDIA AI Infrastructure team focusing on Bayesian neural networks and active learning.

Jiaming’s research has been published in channels such as Nature Communications, JCO Clinical Informatics, NeurIPS, etc. Her work has also been featured in various news channels. In her freetime, she enjoys reading, writing, being out in nature, and learning about other cultures.