I am a Master's graduate from Zhejiang University, currently working as an Algorithm Engineer at Alibaba Taobao & Tmail Group. My research and engineering interests focus on Coding LLMs, LLM Agents & Tool Use, and LLM Post-training.
How to reach me:
- Email: zjuczy2001@163.com
🌱 Current Focus:
- Coding LLM & Agents: Exploring advanced reasoning capabilities and autonomous agent frameworks for software development tasks.
- Post-training Optimization: Investigating SFT (Supervised Fine-Tuning), RLHF, and DPO strategies to enhance model alignment and code generation quality.
💼 Work Experience:
- Algorithm Engineer @ Alibaba Taobao & Tmail Group (Apr 2026 - Present)
🚀 Past Internships:
- R&D Intern @ Alibaba Damo Academy (Dec 2024 - Nov 2025)
- Responsible for LLM post-training research, focusing on data curation and instruction tuning strategies.
- R&D Intern @ 01.AI (Lingyi Wanwu) (Jul 2024 - Dec 2024)
- Worked on Vision-Language Model (VLM) applications, contributing to multimodal understanding and generation tasks.
💬 Ask me about:
- Large Language Models (especially Code LLMs)
- LLM Agents & Tool Use
- Post-training Techniques (SFT, RLHF, DPO)
- Time Series Analysis (My previous research background)
📊 Tech Stack:
