I am a Founding Member of Technical Staff at Eigen AI, where I build systems that make LLM agents better. I lead EigenData, a self-evolving multi-agent platform for synthesizing, auditing, and repairing function-calling data, and EigenLoop, an end-to-end post-training pipeline (SFT, GRPO/RL) for production tool-use agents.

Previously, I was a Research Scientist at Meta (GenAI), where I led agentic post-training that improved Llama 4 Maverick's function-calling BFCL score from ~50 to 72, and an Applied Scientist at Amazon, working on LLM reasoning for e-commerce.

I received my Ph.D. in Computer Science from Georgia Tech / Stanford in 2024, advised by Prof. Diyi Yang. My research spans LLM agents, post-training, and reasoning, with 20+ first-author publications at NeurIPS, ICLR, EMNLP, and ACL.

Research Interests

News