LLM post-training · RLVR · GPU and systems engineering
I’m an engineer at XPENG Robotics, where I work on reinforcement learning
with verifiable rewards (RLVR) for large language models. I hold an M.Eng. in
Electrical and Computer Engineering from the University of Toronto and a
B.A.Sc. in Computer Science from the University of Alberta.
I enjoy turning model-training ideas into reliable systems, with a particular
interest in efficient post-training, inference, and the low-level software that
makes them work.
Hi, I’m Ke Li
LLM post-training · RLVR · GPU and systems engineering
I’m an engineer at XPENG Robotics, where I work on reinforcement learning with verifiable rewards (RLVR) for large language models. I hold an M.Eng. in Electrical and Computer Engineering from the University of Toronto and a B.A.Sc. in Computer Science from the University of Alberta.
I enjoy turning model-training ideas into reliable systems, with a particular interest in efficient post-training, inference, and the low-level software that makes them work.
Current focus
Elsewhere