Experience

  1. Software Engineer Intern

    Google
    • Building agent-based user simulator for multi-turn agent evaluation.
  2. Applied Scientist Intern

    Amazon
    • Designed and implemented a memory-augmented, multi-modal LLM agent-based framework for phishing detection.
  3. Applied Scientist Intern

    Amazon
    • Developed a diffusion model-based account takeover library to mitigate catastrophic forgetting, integrating contrastive loss and a tabular transformer encoder.

Education

  1. PhD Computer Science

    Purdue University
    My research interests lie in LLM-red teaming, RL for security, LLM agents, and backdoor attack/defense.
  2. MSc Electrical and Computer Engineering

    Carnegie Mellon University
    My research focused on explainable reinforcement learning.
  3. BEng Automation

    University of Science and Technology, Beijing