About

I am currently a Research Scientist at Meta working on GenAI systems for feed recommendation, focusing on large language models, reinforcement learning, and agentic workflows for sequence-level personalization, alignment and evaluation. Previously, I was interning as a research data scientist at Microsoft Azure and Tencent America IEGG for one year.

I received my Ph.D. in Statistics from the University of California, Santa Cruz, advised by Prof. Zehang (Richard) Li. My research focuses on the development and application of parametric and non-parametric Bayesian models, with an emphasis on Bayesian latent variable models for prevalence estimation and cause-of-death prediction under domain adaptation (Google Scholar). Prior to my Ph.D., I earned my M.S. in Statistics from the University of California, Davis, where I was advised by Prof. James Sharpnack. Before transitioning into research, I also worked as a full-stack Software Development Engineer at ThoughtWorks, gaining hands-on experience in software engineering, system design, and large-scale data processing.

Research Interests

• LLM post-training and alignment
• Reinforcement learning for personalization
• Agentic workflow design
• Reward modeling under distribution shift
• Online experimentation design and observational study
• Bayesian latent variable modeling
• Causal inference

Selected Works

• Bayesian federated cause-of-death classification and quantification under distribution shift (arXiv 2025)
• Hierarchical latent class models for mortality surveillance using partially verified verbal autopsies (JRSS A, 2025)
• Bayesian tensor decomposition for clustering latent symptom profiles for Verbal Autopsy data (Statistics in Medicine, 2026)
• Treatment effect estimation amidst dynamic network interference in online gaming experiments (arXiv 2024)
• Adaptive reinforcement learning for dynamic configuration allocation in pre-production testing (arXiv 2024)