Zengxiao (Henry) He
LLM inference optimization · Stanford MSEE · GPU systems, serving & kernels
About
I’m an AI infrastructure engineer focused on LLM inference — making large models fast, cheap, and reliable to serve. I care about the systems layer where latency, throughput, and GPU cost are actually decided: serving engines, kernels, batching, and quantization.
My work spans LLM serving platforms, GPU kernel programming (Triton/CUDA), and performance benchmarking for modern inference workloads. At Alibaba Cloud I built backend components for an LLM inference platform; as a Stanford researcher I work on efficient, hardware-inspired AI. Lately I’ve been writing FlashAttention-style fused kernels, building a from-scratch distillation-and-serving stack, and contributing to open-source inference tools like LiteLLM.
I do my best work close to the metal — profiling, measuring, and squeezing tokens/sec out of real hardware. Outside of work, I’m usually playing fingerstyle guitar, on a tennis court, or learning performance driving.
Experience
Research Assistant — Efficient AI
Stanford University — Prof. Tom Lee
Research on efficient AI and hardware-inspired neural computation. Building Python/PyTorch simulation and evaluation pipelines for sparse architectures and their inference behavior — where model design meets serving efficiency.
Teaching Assistant (CS 295: Software Engineering)
Stanford University
Teaching and mentoring students on building robust software systems alongside Prof. Sara Achour. Designing assignment workflows, reviewing LLM-generated code for correctness, and providing project feedback to students.
Co-Founder & Full-Stack Engineer
Glowia AI
Built a conversational AI agent for MedSpa customer engagement — Instagram DM intake, appointment booking, deposits, and operator monitoring — over configurable LLM inference pipelines tuned for cost and latency.
Software Engineer Intern — AI/ML
Oracle
Developed and deployed an AI-powered automation agent for Oracle's supply chain platform, integrating Node.js, Puppeteer, Slack API, OCI Queues, Docker CI/CD, and a local Llama-4 runtime for root-cause generation to cut backport processing time by 40%.
Software Engineer Intern — LLM Inference Infrastructure
Alibaba Cloud
Worked on an LLM inference platform for model serving and deployment. Built and maintained backend components for inference service orchestration and request routing in C++/Python/Java — hands-on with LLM serving systems, latency-sensitive services, and cloud AI infrastructure.
Projects
Skills
Writing
Education
Stanford University
M.S. in Electrical Engineering — GenAI Inference Optimization
GPA: 3.8/4.0. Teaching Assistant for CS 295 Software Engineering.
Central South University
B.Eng. in Software Engineering
GPA: 3.9/4.0. Core Member, National Innovation & Entrepreneurship Base.