Biography

I work for claws.

My work sits at the intersection of reinforcement learning and ML systems, with a particular interest in RL infra, LLM inference, and production ML serving. I am currently a Machine Learning Engineer at Meta, working on production ranking systems in Core Ads Growth.

Previously, I worked on foundation model for game agents at Tencent, ML systems research for LLM inference at Carnegie Mellon University, and earlier reinforcement learning research on portfolio optimization. Across these experiences, I have been most motivated by building efficient and reliable systems that make learning-based agents practical in the real world.

Mail GitHub LinkedIn Instagram Blog

News

[2025/02] Joined Meta as a Machine Learning Engineer on Creative Ranking team!
[2024/08] Wrapped up an exciting summer at Meta, where I worked on multimodal LLM for audience targeting.
[2023/06] Our paper on interpretable stochastic reinforcement learning for portfolio optimization was accepted by Applied Intelligence.

Education

Carnegie Mellon University Aug 2023 - Dec 2024

MS, AI Engineering, Electrical and Computer Engineering

University of Liverpool Sep 2019 - Jul 2023

BS, Computer Science

Industry Experience

Meta

Machine Learning Engineer, Creative Ranking, Core Ads Growth Feb 2025 - Present

Optimize large-scale production ranking and delivery infrastructure, with a focus on serving efficiency, scalability, and reliability.

Software Engineer Intern, Machine Learning, Creative Delivery, Core Ads Growth May 2024 - Aug 2024

Worked on multimodal LLM-driven audience targeting in early-stage delivery systems.

Tencent Jun 2022 - Oct 2022

Machine Learning R&D Intern, Game AI Research Center

Worked on the PUBG game AI agent with supervised pretraining with RL post-training to improve human-like behavior.

Research Experience

Infini-AI Lab, Carnegie Mellon University Jul 2024 - Dec 2024

Research Intern, ML Systems

Advised by Prof. Chen Beidi.
Conducted research on accelerating LLM inference using speculative decoding.

University of Liverpool Jan 2021 - Aug 2022

Research Intern, Reinforcement Learning

Conducted reinforcement learning research for portfolio optimization, with a focus on stochastic policies, robust sequential decision-making, and interpretable agent behavior.
Co-authored a paper on interpretable stochastic model-free RL for portfolio optimization, published in Applied Intelligence [paper].