Skip to main content

Daehyeok Kim

Assistant Professor

Dr. Daehyeok Kim is an Assistant Professor of Computer Science at the University of Texas at Austin. He co-leads the UT Networked Systems Research Group and is also a member of the InfraAI Center, the Wireless Networking and Communications Group, and 6G@UT. He is a co-PI of the LDOS NSF Expeditions in Computing project. Prior to joining UT Austin, he was a Senior Researcher at Microsoft Research Redmond. He received his Ph.D. in Computer Science from Carnegie Mellon University.

Research

Research Areas:
Research Interests:
  • Computer networks
  • Operating systems
  • Distributed systems
Current Research:
Dr. Kim develops programmable, efficient, and resilient computing infrastructure for diverse applications, including AI training and inference, as well as real-time interactive services. His research spans datacenters and the network edge, with three main areas:
  • Datacenter infrastructure for AI and cloud: Making NICs, switches, and GPU fabrics programmable, managing and isolating their shared resources like an operating system, and keeping workloads running through failures.
  • Real-time edge computing: Making computing at the network edge SLO-aware, secure, and resilient for real-time applications, from live video analytics to live generative AI.
  • Profiling, modeling, and testing systems: Building efficient profilers to drive resource-management decisions, high-fidelity simulators, and generators of realistic workloads and testing environments.
Research Labs & Affiliations:

Select Publications

Joon Ha Kim, Geon-Woo Kim, Anoop Rachakonda, Daehyeok Kim. Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation. In Proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS), December 2026.

Donghyun Kim, Zichao Hu, Joydeep Biswas, Aditya Akella, Daehyeok Kim. Mimesys: Generating Realistic Executable Testing Environments from Resource Usage Traces. In Proceedings of the 20th USENIX Symposium on Operating Systems Design and Implementation (OSDI), July 2026.

Xiao Zhang, Daehyeok Kim. Enabling SLO-Aware 5G Multi-Access Edge Computing with SMEC. In Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation (NSDI), April 2026.

Jiaxin Lin, Zhiyuan Guo, Mihir Shah, Tao Ji, Yiying Zhang, Daehyeok Kim, and Aditya Akella. Portable and High-Performance SmartNIC Programs with Alkali. In Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI), April 2025.

Jiarong Xing, Sophia Yoo, Xenofon Foukas, Daehyeok Kim, and Michael K. Reiter. On the Criticality of Integrity Protection in 5G Fronthaul Networks. In Proceedings of the 33rd USENIX Security Symposium, August 2024.

View complete list

Awards & Honors

  • 2025 - NSF CAREER Award
  • 2025 - NVIDIA Academic Grant Award
  • 2019 - Microsoft Research PhD Fellowship
  • 2018 - Bronze Award, the 24th Samsung HumanTech Paper Award
  • 2016 - Qualcomm Innovation Awards

Contact Info

Daehyeok Kim
Assistant Professor
Homepage
daehyeok@utexas.edu
GDC 6.824
CV

Related Stories

Daehyeok Kim Wins National Research Award for Advancing Cloud Hardware Efficiency
Keeping Up with AI’s Increasingly Complex Networking Demands
NSF Funded Expedition Project Uses AI to Rethink Computer Operating Systems
More stories