I am an AI-native Solutions Architect and HPC System Engineer at NVIDIA, where I have worked since January 2026. I received my Ph.D. in Computer Science from Texas Tech University. During my doctoral studies, I was a member of the Data-Intensive Scalable Computing Laboratory (DISCL), led by Dr. Yong Chen. I also collaborated with Dr. Wei Zhang at the Texas Advanced Computing Center and Dr. Suren Byna at The Ohio State University. My research focuses on high-performance computing (HPC), energy-efficient computing frameworks, AI inference on HPC systems, and scientific data management.

💼 Experience

2026.01 - Present, AI-native Solutions Architect and HPC System Engineer, NVIDIA

📖 Education

2019.06 - 2025.12, PhD, Computer Science, Texas Tech University, Lubbock, Texas
2015.09 - 2018.06, Master, Information Science and Technology, University of Science and Technology of China, China
2011.09 - 2015.06, Bachelor, Mathematics, University of Science and Technology of China, China

🔥 News

2026.07 My paper MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration. has been accepted for presentation at ICCAD 2026.
2026.07 My paper Power-Centric Observability for HPC Systems: Design, Deployment, and Evaluation on REPACSS. has been published in the Proceedings of PEARC 2026.
2026.04 My paper TokenPowerBench: Benchmarking the Power Consumption of LLM Inference. has been published in the Proceedings of AAAI 2026 (acceptance rate: 17.6%).
2026.04 My paper FIXME: Towards End-to-End Benchmarking of LLM-Aided Design Verification. has been published in the Proceedings of AAAI 2026 (acceptance rate: 17.6%).

📝 Selected Publications

View all publications

AAAI 2026

TokenPowerBench: Benchmarking the Power Consumption of LLM Inference.

Chenxu Niu, Wei Zhang, Jie Li, Yongjian Zhao, Tongyang Wang, Xi Wang, and Yong Chen.

PDF| Code| DOI| BibTeX| Poster

AAAI 2026

FIXME: Towards End-to-End Benchmarking of LLM-Aided Design Verification.

Gwok-Waa Wan, SamZaak Wong, Shengchu Su, Chenxu Niu, Ning Wang, Xinlai Wan, Qixiang Chen, Mengnv Xing, Jingyi Zhang, Jianmin Ye, Yubo Wang, Rongchang Song, Tao Ni, Qiang Xu, Nan Guan, Zhe Jiang, Xi Wang, Yong Chen, and Jun Yang.

PDF| DOI| BibTeX

HotCarbon 2025

Energy Efficient or Exhaustive? Benchmarking Power Consumption of LLM Inference Engines.

Chenxu Niu, Wei Zhang, Yongjian Zhao, and Yong Chen.

PDF| Code| DOI| BibTeX

PEARC 2026

Power-Centric Observability for HPC Systems: Design, Deployment, and Evaluation on REPACSS.

Yongjian Zhao, Jie Li, Chenxu Niu, Alan Sill, and Yong Chen.

PDF| DOI| BibTeX

🧰 Selected Projects

View all projects

TokenPowerBench

Open-source benchmark suite

Measures LLM inference power consumption across single-node and multi-node GPU settings, with phase-aware metrics for prefill and decode.

LLM Inference Power Benchmarking Multi-Node GPU

Code| Paper| DOI

LLM Inference Engine Benchmark

Open-source benchmarking tool

Benchmarks energy consumption and efficiency trade-offs across LLM inference engines including vLLM, DeepSpeed, TensorRT-LLM, and Transformers.

LLM Systems Inference Engines Energy Efficiency

Code| Paper| DOI

💬 Professional Service

Program Committee Member: AAAI ’27, AAAI ’26, PEARC ’26
Reproducibility Committee Member: SC ’25
Paper Reviewer: AAAI ’27, AAAI ’26, ACM TiiS ’26, BigData ’25, CCGrid ’24, SSDBM ’24
Conference Volunteer: SC ’21, SC ’24