[go: up one dir, main page]

About

Jin Heo is a Senior Researcher at Dolby Laboratories and holds a Ph.D. in Computer Science from Georgia Institute of Technology, where he conducted research in ML inference serving, adaptive resource management, and distributed systems under Prof. Ada Gavrilovska. His research focuses on efficiently serving real-time workloads under resource and latency constraints, with applications spanning XR, cloud gaming, and real-time perception. At Dolby, he extends this work to production-scale systems, architecting ML-enabled cloud and streaming infrastructure from research models to distributed service deployment.

Technical Expertise & Focus

  • ML Inference Serving & Adaptive Resource Management: Designing real-time inference serving and scheduling systems that adapt resource allocation to workload dynamics, result effectiveness, and resource constraints.
  • Real-Time & Distributed Systems: Building distributed systems for latency-sensitive workloads across resource-constrained edge and scalable cloud environments, with applications in XR, cloud gaming, and streaming perception.
  • ML & Cloud Infrastructure: Architecting end-to-end ML-enabled cloud systems, including distributed microservices, model deployment, infrastructure orchestration, and high-throughput streaming data pipelines.

Background

His interest in systems and immersive computing grew from an early career as a professional gamer, which sparked his curiosity about the intersection of computer science, games, and interactive experiences. This early interest ultimately led to research on high-performance systems for XR, cloud gaming, and real-time perception.

์†Œ๊ฐœ

ํ—ˆ์ง„ (Jin Heo) ๋Š” ํ˜„์žฌ Dolby Laboratories์˜ Senior Researcher๋กœ ์žฌ์ง ์ค‘์ด๋ฉฐ, Georgia Institute of Technology์—์„œ ์ปดํ“จํ„ฐ๊ณผํ•™ ๋ฐ•์‚ฌํ•™์œ„๋ฅผ ๋ฐ›์•˜์Šต๋‹ˆ๋‹ค. Georgia Tech์—์„œ๋Š” Ada Gavrilovska ๊ต์ˆ˜์˜ ์ง€๋„ ์•„๋ž˜ ML inference serving, adaptive resource management, distributed systems๋ฅผ ์—ฐ๊ตฌํ–ˆ์Šต๋‹ˆ๋‹ค. ์ฃผ์š” ์—ฐ๊ตฌ๋Š” ์ž์› ๋ฐ ์ง€์—ฐ์‹œ๊ฐ„ ์ œ์•ฝ์ด ์žˆ๋Š” ํ™˜๊ฒฝ์—์„œ ์‹ค์‹œ๊ฐ„ ์›Œํฌ๋กœ๋“œ๋ฅผ ํšจ์œจ์ ์œผ๋กœ ์ฒ˜๋ฆฌํ•˜๊ณ  ์„œ๋น™ํ•˜๋Š” ์‹œ์Šคํ…œ์— ์ดˆ์ ์„ ๋‘๋ฉฐ, XR, ํด๋ผ์šฐ๋“œ ๊ฒŒ์ด๋ฐ, ์‹ค์‹œ๊ฐ„ perception ๋“ฑ์˜ ์‘์šฉ ๋ถ„์•ผ๋ฅผ ๋‹ค๋ฃน๋‹ˆ๋‹ค. Dolby์—์„œ๋Š” ์ด๋Ÿฌํ•œ ์—ฐ๊ตฌ ๊ฒฝํ—˜์„ production-scale ์‹œ์Šคํ…œ์œผ๋กœ ํ™•์žฅํ•˜์—ฌ, ์—ฐ๊ตฌ ๋ชจ๋ธ๋ถ€ํ„ฐ ๋ถ„์‚ฐ ์„œ๋น„์Šค ๋ฐฐํฌ๊นŒ์ง€ ์•„์šฐ๋ฅด๋Š” ML ๊ธฐ๋ฐ˜ ํด๋ผ์šฐ๋“œ ๋ฐ ์ŠคํŠธ๋ฆฌ๋ฐ ์ธํ”„๋ผ๋ฅผ ์„ค๊ณ„ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.

์ฃผ์š” ์—ฐ๊ตฌ ๋ถ„์•ผ ๋ฐ ๊ธฐ์ˆ 

  • ML Inference Serving & Adaptive Resource Management: ์›Œํฌ๋กœ๋“œ์˜ ๋ณ€ํ™”, inference ๊ฒฐ๊ณผ์˜ effectiveness, ๊ทธ๋ฆฌ๊ณ  ์‹œ์Šคํ…œ์˜ ์ž์› ์ œ์•ฝ์— ๋”ฐ๋ผ ์ž์› ํ• ๋‹น์„ ๋™์ ์œผ๋กœ ์กฐ์ •ํ•˜๋Š” ์‹ค์‹œ๊ฐ„ inference serving ๋ฐ scheduling ์‹œ์Šคํ…œ์„ ์„ค๊ณ„ํ•ฉ๋‹ˆ๋‹ค.
  • Real-Time & Distributed Systems: ์ง€์—ฐ์‹œ๊ฐ„์— ๋ฏผ๊ฐํ•œ ์›Œํฌ๋กœ๋“œ๋ฅผ resource-constrained edge ํ™˜๊ฒฝ๋ถ€ํ„ฐ scalable cloud ํ™˜๊ฒฝ๊นŒ์ง€ ํšจ์œจ์ ์œผ๋กœ ์ฒ˜๋ฆฌํ•˜๊ธฐ ์œ„ํ•œ ๋ถ„์‚ฐ ์‹œ์Šคํ…œ์„ ๊ตฌ์ถ•ํ•˜๋ฉฐ, XR, ํด๋ผ์šฐ๋“œ ๊ฒŒ์ด๋ฐ, streaming perception ๋“ฑ์˜ ์‘์šฉ ๋ถ„์•ผ๋ฅผ ๋‹ค๋ฃน๋‹ˆ๋‹ค.
  • ML & Cloud Infrastructure: ๋ถ„์‚ฐ ๋งˆ์ดํฌ๋กœ์„œ๋น„์Šค, ๋ชจ๋ธ ๋ฐฐํฌ, ์ธํ”„๋ผ ์˜ค์ผ€์ŠคํŠธ๋ ˆ์ด์…˜, ๋Œ€๊ทœ๋ชจ ์ŠคํŠธ๋ฆฌ๋ฐ ๋ฐ์ดํ„ฐ ํŒŒ์ดํ”„๋ผ์ธ ๋“ฑ์„ ํฌํ•จํ•˜๋Š” end-to-end ML ๊ธฐ๋ฐ˜ ํด๋ผ์šฐ๋“œ ์‹œ์Šคํ…œ์„ ์„ค๊ณ„ํ•ฉ๋‹ˆ๋‹ค.

๋ฐฐ๊ฒฝ

ํ”„๋กœ๊ฒŒ์ด๋จธ๋กœ์„œ์˜ ์ดˆ๊ธฐ ๊ฒฝํ—˜์„ ๊ณ„๊ธฐ๋กœ ์‹œ์Šคํ…œ๊ณผ immersive computing์— ๊ด€์‹ฌ์„ ๊ฐ–๊ฒŒ ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. ๋‹น์‹œ ์ปดํ“จํ„ฐ๊ณผํ•™๊ณผ ๊ฒŒ์ž„ ๋ฐ ์ธํ„ฐ๋ž™ํ‹ฐ๋ธŒ ๊ฒฝํ—˜์˜ ์ ‘์ ์— ๊ด€์‹ฌ์„ ๊ฐ€์ง€๊ฒŒ ๋˜์—ˆ๊ณ , ์ด๋Ÿฌํ•œ ๊ด€์‹ฌ์€ ์ดํ›„ XR, ํด๋ผ์šฐ๋“œ ๊ฒŒ์ด๋ฐ, ์‹ค์‹œ๊ฐ„ perception์„ ์œ„ํ•œ ๊ณ ์„ฑ๋Šฅ ์‹œ์Šคํ…œ ์—ฐ๊ตฌ๋กœ ์ด์–ด์กŒ์Šต๋‹ˆ๋‹ค.

Resume *updated Aug, 2026

Jin Heo

Publications

Experience

๊ฒฝ๋ ฅ

Services & Activities

ํ•™์ˆ  ํ™œ๋™ ๋ฐ ๊ธฐํƒ€ ํ™œ๋™

Education

  • Georgia Tech, Ph.D., Computer Science, Aug 2019 - Aug 2025, PhD Thesis: "Adaptively Serving XR Workloads from Resource-constrained Edge" [๐Ÿ“„ paper]
  • Ajou University, B.S., Computer Software and Engineering, Mar 2016 - Aug 2018

ํ•™๋ ฅ

  • ์กฐ์ง€์•„ ๊ณต๊ณผ๋Œ€ํ•™๊ต (Georgia Tech), ์ปดํ“จํ„ฐ ๊ณผํ•™ ๋ฐ•์‚ฌ, 2019๋…„ 8์›” - 2025๋…„ 8์›”, ํ•™์œ„ ๋…ผ๋ฌธ: "Adaptively Serving XR Workloads from Resource-constrained Edge" [๐Ÿ“„ paper]
  • ์•„์ฃผ๋Œ€ํ•™๊ต, ์ปดํ“จํ„ฐ ์†Œํ”„ํŠธ์›จ์–ด ๊ณตํ•™ ํ•™์‚ฌ, 2016๋…„ 3์›” - 2018๋…„ 8์›”
  • ํ•™์ ์€ํ–‰์ œ, ์ •๋ณด์ฒ˜๋ฆฌ ์ „๋ฌธํ•™์‚ฌ, 2015๋…„ 3์›” - 2016๋…„ 2์›”
  • ์ฒญ๊ฐ•๋ฌธํ™”์‚ฐ์—…๋Œ€ํ•™๊ต, ๊ฒŒ์ž„์ „๊ณต (1ํ•™๋…„ ์žฌํ•™), 2011๋…„ 3์›” - 2014๋…„ 12์›”

Recent Posts

์ตœ๊ทผ ๊ธ€

Blog Renewal

I have created and modified my blog with github page with some fancy themes a couple of times, but such fancy themes were annoying for me to maintain. So, all the complexities are totally wiped out through this renewal, and I hope my life would get easier.

August 3, 2021 ยท 1 min ยท Jin Heo ยท