About
I am a third-year PhD student at Georgia Tech advised by Prof. Moinuddin Qureshi. My research focuses on computer architecture and systems for AI workloads. My recent work includes data movement optimization in CPU-GPU systems for LLM inference, GPU memory system design for emerging memory technologies such as High-Bandwidth Flash, and efficient mixture-of-experts inference.
You can view my CV here.
Education
-
2024–2029 (Expected) Georgia Institute of Technology, Atlanta, United States
PhD in Electrical and Computer Engineering -
2018–2024 Seoul National University (SNU), Seoul, South Korea
BS in Electrical and Computer Engineering
Work Experience
Microsoft
Research Intern
May 2026 - Aug 2026
- Analyzed scale-out network bottlenecks in shared KV cache storage using GitHub Copilot agentic traces.
- Developed a multi-rack simulator to design GB200/VR200 NVL72 servers for agentic workloads.
Qualcomm
Engineering Intern
May 2025 - Aug 2025
- Improved traceability in the ExecuTorch AI compiler for edge devices.
- Developed an automated tracing tool of torch.fx graph transformations with negligible overhead.
- Developed multi-GPU acceleration for Llama 2 and ResNet-18 under fully homomorphic encryption (FHE).
- Designed the initial architecture and abstractions for a new FHE library.
Publications*Equal contribution
-
TileLens: Efficiently Using Large-Granularity Memory Systems with Transparent Two-Dimensional Memory Layout
*Jae Hyung Ju, *Euijun Chung, Hritvik Taneja, Anish Saxena, Shinnung Jeong, Hyesoon Kim, and Moinuddin Qureshi
IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2027 -
Making Locality-Aware GEMM Compatible With Page-Granularity Placement on Chiplet GPUs
Euijun Chung, Jae Hyung Ju, and Hyesoon Kim
IEEE Computer Architecture Letters (CAL), 2026 -
Piccolo: Large-Scale Graph Processing with Fine-Grained In-Memory Scatter-Gather
Changmin Shin, Jaeyong Song, Hongsun Jang, Dogeun Kim, Jun Sung, Taehee Kwon, Jae Hyung Ju, Frank Liu, Yeonkyu Choi, and Jinho Lee
IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2025 -
NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrapping
*Jae Hyung Ju, *Jaiyoung Park, Jongmin Kim, Minsik Kang, Donghwan Kim, Jung Hee Cheon, and Jung Ho Ahn
ACM Conference on Computer and Communications Security (CCS), 2024 -
A Case for In-Memory Random Scatter-Gather for Fast Graph Processing
Changmin Shin, Taehee Kwon, Jaeyong Song, Jae Hyung Ju, Frank Liu, Yeonkyu Choi, and Jinho Lee
IEEE Computer Architecture Letters (CAL), 2024
Preprints
-
BOOST: Concurrent Access to Host Memory and HBM to Accelerate LLM Inference
*Anish Saxena, *Jae Hyung Ju, Hritvik Taneja, Po-An Tsai, Aamer Jaleel, Christos Kozyrakis, and Moinuddin Qureshi
arXiv preprint arXiv:2609.13592, 2026 -
SiFAR: Synchronization-Free All-Reduce for Low-Latency LLM Inference
Hritvik Taneja, Anish Saxena, Abhishek Revinipati, Jae Hyung Ju, Neal C. Crago, and Moinuddin Qureshi
arXiv preprint arXiv:2607.08973, 2026 -
Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection
Vima Gupta, Jae Hyung Ju, Kartik Sinha, Ada Gavrilovska, and Anand Iyer
arXiv preprint arXiv:2411.08982, 2026 -
NeuralEQ: Neural-Network-Based Equalizer for High-Speed Wireline Communication
Hanseok Kim, Jae Hyung Ju, Hyun Seok Choi, Hyeri Roh, and Woo-Seok Choi
arXiv preprint arXiv:2308.02133, 2023
Patents
-
Electronic device, server device for handling homomorphic encrypted data, and methods thereof
Jae Hyung Ju, Jaiyoung Park, Jung Hee Cheon, and Jung Ho Ahn
U.S. Patent Application Publication 2026/0012327 A1, Jan. 2026 -
Server device for handling homomorphic encrypted data, and methods thereof
Jae Hyung Ju, Jaiyoung Park, Jung Hee Cheon, and Jung Ho Ahn
U.S. Patent Application Publication 2026/0012326 A1, Jan. 2026