# Wang Tong / 王通

LLM post-training and agent algorithm engineer focused on alignment, RL, reward modeling, synthetic data, self-play, rejection sampling, and evaluation harnesses.

## Contact

- GitHub: https://github.com/wangtong10086
- LinkedIn: https://www.linkedin.com/in/%E9%80%9A-%E7%8E%8B-190ba329a/
- Email: wangtong91347625@gmail.com