Apr 2025 – Present
Senior AI Scientist
LinkedIn · Sunnyvale, CA
LLM post-training, agentic reinforcement learning
About
I am a Senior AI Scientist at LinkedIn, working on LLM post-training and agentic reinforcement learning. I received my Ph.D. in Electrical Engineering from Columbia University in 2024, where I was advised by Prof. James Anderson.
My research focuses on LLM post-training, federated learning, reinforcement learning, control theory, and large-scale optimization. The primary goal of my research is to enable reliable and efficient learning and decision-making in large-scale distributed systems.
Experience
Nov 2024 – Apr 2025
Machine Learning Engineer
ByteDance · San Jose, CA
Ads ranking and bidding algorithms
Publications
See Google Scholar for a complete list.
2024
ICLR
Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
International Conference on Learning Representations (ICLR), 2024
ICML
Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments
International Conference on Machine Learning (ICML), 2024
L4DC
Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQR
Learning for Dynamics and Control (L4DC), Oxford, UK, 2024 🏆 Best Paper Award
2023
NeurIPS
Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates
Neural Information Processing Systems (NeurIPS), 2023
Academic Service
I serve as a reviewer for the following venues:
- NeurIPS Conference on Neural Information Processing Systems
- ICML International Conference on Machine Learning
- ICLR International Conference on Learning Representations
Education
2020 – 2024
2018 – 2020
M.S., Applied Mathematics and Computational Science
University of Pennsylvania
Honors & Awards
- Best Paper Award, Learning for Dynamics and Control (L4DC), Oxford, UK, 2024
- Wei Family Scholarship, Wei Family Foundation, 2020
- Departmental Fellowship for Outstanding PhD Students, Columbia University