CV

experience

• 2021.03 – 2026.08

  VUNO Inc.

  AI Research Scientist

  • Developed and improved the classification and segmentation models shipped in a commercial computer vision product.
  • Built CPU-only inference optimization and asynchronous model serving for GPU-less deployment.
  • Automated the release pipeline and established a 23-dataset benchmark as the release quality gate.
  • Won two international challenges and published at ICLR, MICCAI, BMVC, ISBI and SCIE journals.
  • Built the evaluation platform and inference backend for multi-site reader studies.
• 2019.03 – 2021.02

  Hanyang University, Computer Vision Lab

  M.S. Researcher

  • Object detection and tracking, domain generalization, deep hashing for multi-label retrieval.
  • Published at ICLR 2020 and three domestic conferences, two as first author.

education

• 2019 – 2021

  Hanyang University

  M.S., Computer Software

  Computer Vision Lab, advised by Jongwoo Lim · GPA 4.25/4.5

  Deep Hashing Specialized for Multi-Label Image Retrieval

• 2015 – 2019

  Hanyang University

  B.S., Software

  Overall 3.71/4.5 · Major 3.83/4.5

awards

• 2024.05

  1st place · JustRAIGS — AI Glaucoma Screening Challenge ISBI 2024

  322 participants from 37 countries; first overall among 20 teams in the final phase. Two tasks: binary classification of referral need and multi-label classification of ten fine-grained features.

• 2022.09

  1st place · DRAC22 — Diabetic Retinopathy Analysis Challenge MICCAI 2022

  First place in all three tasks: multi-class segmentation of fine structures, image-quality classification, and severity grading.

• 2016.11

  Bronze · ACM-ICPC Korea Regional ACM

patents

• 2023.12

  Method and apparatus for providing lesion information

  Filed · 10-2023-0184784

• 2023.10

  Method and apparatus for transferring the style of an image

  Granted · 10-2592666

• 2021.03

  Object tracking method using hard negative mining

  Granted · 10-2224101

technical

Modeling

PyTorch · Lightning · Classification / Segmentation / Detection · Multi-Task Learning · Semi- & Weakly-supervised Learning · Self-supervised Learning (MAE) · OOD Detection · Class Imbalance

Generative & LLM

Diffusion (text/mask-conditioned) · LoRA / QLoRA · VLM Fine-tuning · vLLM · AWQ · LangGraph · LangChain

Serving & MLOps

OpenVINO · ONNX · Celery · Redis · Docker · GitHub Actions · MLflow · W&B · Optuna · Multi-GPU (DDP)

Languages

Python · TypeScript · C/C++

Etc.

Military service completed (Technical Research Personnel, 2021–2024) · JLPT N3