Daehyeok Kim
University of Texas at Austin, TX·Computer Science·Early-career
Modern computing increasingly depends on moving work to the right place: onto network hardware, onto nearby servers, or onto custom-built data paths. The lab designs systems software that makes this offloading practical.
- Fields
Computer Science
Engineering
- Topics
computer networking
computer systems
edge computing
- Grants
- 3 known grants, through Jun 2030
What they work on
- Create a programming model that describes robot manipulation tasks as cooperating control loops with explicit deadlines and recovery from robot and network failures.
- Build a compiler and runtime that split, schedule and scale control loops between farm robots and edge servers over a private cellular network, plus a graph neural network that diagnoses problems.
- Design NicOS abstractions for managing on-chip resources, memory and communication channels on programmable network interface cards, with elastic scaling and in-place data structure resizing.
- Ensure performance and security isolation among cloud tenants sharing a NIC through a virtual channel scheduler and privileged access controls, prototyped on software, NPU-based and FPGA-based NICs.
- Develop the Transcraft framework, which uses formal specification and verification to automatically synthesize network transport designs, with reusable transport templates and workload benchmarks.
More about the research
Its three projects cover farm robots that rely on a nearby computer over a cellular network, network cards shared by many cloud users, and a framework for building the data-transport layer that AI and supercomputing jobs need.
Why it matters
Low-cost farm robots supported by shared edge computing could make automation affordable for small and medium farms, easing labor shortages. Through more precise plant care, they could also reduce water, fertilizer and pesticide use. Shareable network cards could help cloud providers get more from existing hardware as demand for computing grows. Faster tools for building network transport could speed up data movement for AI and supercomputing workloads.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
CAREER: Toward Programmable NICs as Multi-Tenant Cloud Resources
NSF · Jul 2025 – Jun 2030
VINES: Track 1: Enabling Real-Time Agricultural Robotics with AI-Native Cellular Access Edge
NSF · Oct 2026 – Sep 2029
NeTS: Medium: An End-to-End Framework for Network Transport Design and Implementation for Emerging Applications
NSF · Jul 2024 – Jun 2028
Closest labs
Arvind Krishnamurthy
University of Washington, WA·Computer Science
Design NetFusion, a rack-level pool of programmable network interface cards (SmartNICs) that perform packet and network-function processing for many servers, with safe and fair sharing among applications.
Zhi-Li Zhang
University of Minnesota, MN·Computer Science
Develop an O-RAN-based framework in which 5G networks use vehicle trajectory and speed to proactively cut delays from poor radio signals and base-station handovers during remote driving.
Paul Ruth
University of North Carolina at Chapel Hill, NC·Computer Science
Deploy next-generation SmartNICs, programmable network cards called Data Processing Units, at four international FABRIC testbed sites so researchers can offload networking, storage and security tasks from CPUs and GPUs.
The school
University of Texas at Austin: 49 labs on PI Pages, $1.1B a year on research, 871 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.