Hyogeun Oh (오효근)
INTRODUCTION
🌱 Continuously Growing Engineer
Passionate about learning and growth, I manage a technical blog featuring over 200 articles on various topics, including Kubernetes, PyTorch, and Airflow. Additionally, I participate in more than 10 study groups. I take great pleasure in delving into the core principles of technology and leveraging them to address real-world challenges.
🚀 Efficiency-Maximizing Engineer
I strive to automate inefficient repetitive processes and seek more efficient methods for operational improvement. I have developed libraries for frequently used functionalities and built a sustainable deployment system through the construction of CI/CD pipelines.
🫂 Collaboration-Focused Engineer
I have integrated project source codes using Git Submodules to facilitate a smooth collaborative environment. Additionally, I have incorporated MLOps tools such as DVC and MLflow into team workflows, significantly improving our collaborative efforts on data and models, and fostering a productive team environment.
Latest Updated 2024. 05. 17 (D+0)
Zerohertz
SKILLS
Programming
- 3 Python
- 3 MATLAB
- 2 C, C++
- 2 Cython
- 2 R
- 1 Go
- 1 Java
MLOps
- 2 Triton Inference Server
- 2 TensorRT
- 2 ONNX
- 2 Amazon EC2 Inf1
- 1 Kubeflow
- 1 MLflow
- 1 DVC
Infra
- 3 Docker
- 2 Kubernetes
- 1 Argo CD
- 1 GitHub Actions
- 1 Grafana
- 1 Prometheus
- 1 Traefik
Data Engineering
- 2 Apache Airflow
- 1 Apache Kafka
Database
- 1 MySQL
- 1 PostgreSQL
Etc
- Ansys
- Arduino
- Catia
- LabVIEW
- Raspberry Pi
- Unreal Engine
EXPERIENCES Total 1 year 4 months
2023. 02 ~
Current1 yr 4 mos
AgileSoDA
Machine Learning Research Engineer- Developed and deployed various models for text, signature, and checkbox detection, as well as information extraction, for the AI optical character recognition (OCR) product TwinReader.
- Developed Python backend for model serving and optimized pipelines for increased efficiency.
- Maintained and managed Kubernetes-based clusters.
- Executed AI projects and proof of concept (PoC) to meet client specifications.
- Skill KeywordsPythonDockerKubernetesResearchMachine Learning
2021. 03 ~ 2023. 02
2 yrs 0 mo
SiM Lab. (Smart intelligent Manufacturing system Laboratory)
Research Student- Conducted research and development on diagnostic models for monitoring various process conditions.
- Developed a graphical user interface (GUI) for real-time monitoring.
- Performed computational fluid dynamics (CFD) simulations based on tension and temperature in roll-to-roll continuous processes.
- Skill KeywordsPythonMATLABAnsysResearchMachine Learning
2019. 11 ~ 2021. 02
1 yr 4 mos
SiM Lab. (Smart intelligent Manufacturing system Laboratory)
Research Intern- Developed bearing condition diagnostic model and graphic user interface.
- Skill KeywordsMATLABResearchMachine Learning
2018. 06 ~ 2019. 11
1 yr 6 mos
MRV Lab. (Medical Robotics and Virtual Reality Laboratory)
Research Intern- Developed virtual reality environments based on Unreal Engine.
- Skill KeywordsUnreal EngineC++Research
PROJECTS
2024. 02 ~
Trade Document Information Extraction Model
AgileSoDA- Developed an AI OCR-based document classification pipeline for categorizing unstructured document data.
- Accelerated data annotation through Label Studio SDK and pre-labeling.
- Developed a Streamlit-based GUI for reviewing through annotations with challenging requirements
- Developed models tailored to the specific needs of clients and types of trade documents.
2023. 11 ~
Development and CI/CD Pipeline Construction of Python Library
Personal Project
2023. 10 ~
Python Library for Pre/Post-Processing, Visualization, and Model Backend
AgileSoDA- Performed documentation of functions and classes within the library based on Docstring.
- Maintained the integrity of the library through type hints and PyTest.
- Standardized the preprocessing of various document images and visualization of model inference results.
- Improved the post-processing speed of the text detection model through algorithm enhancements using Cython. (inference time decreased by 74.12%)
- Developed a unified class and inheritance structure for Triton Inference Server.
2023. 02 ~
AI-based OCR Solution, TwinReader
AgileSoDA- Developed models for document area detection, rotated document classification, and detection of text, signatures, checkboxes.
- Solved misclassification issues of rotated documents through model structural improvements. (accuracy improved by 2.01%)
- Developed a Kubernetes-based Triton Inference Server for model deployment.
- Enhanced inference time of the text detection model using TensorRT. (inference time decrease by 87.31%)
- Fixed critical flaws in the Triton Inference Server. (GPU Memory reduced by 47.9%)
2023. 11 ~ 2024. 02
AI-based Automotive Damage and Depth Recognition Product, TwinCar
AgileSoDA- Developed a vehicle type classification model for PoC execution.
- Conducted research and development models for filter, part recognition, repair type, and damage type, along with the model inference pipeline.
- Developed a demo page using Streamlit and deployed it on Kubernetes.
2023. 04 ~ 2023. 11
AI Diagnostic Service for Burn Patients
AgileSoDA- Developed models for segmentation of burn areas and severity diagnosis in burn patients.
- Designed and developed an API for model deployment using Triton Inference Server.
2023. 08 ~ 2023. 09
Construction of a Kubernetes Cluster
Personal Project
2023. 01 ~ 2023. 07
Mosaic Classification
BOAZ- Team-BoonMoSa (GitHub)
- Developed a YOLOv5 based logo segmentation model.
- Constructed a model deployment server on Amazon EC2 Inf1.
PUBLICATIONS & PATENT
2023. 09
- [Patent] Apparatus and method for predicting coating layer thickness in slot-die coating process
- Inventor: Changwoo Lee, Minho Jo, Yoonjae Lee, Hyogeun Oh
- Application number: 1020220017419 (2022.02.10)
- Grant number: 1025842600000 (2023.09.25)
2023. 01
- [SCI(E)] Classification and Redundancy Quantitative Evaluation Algorithm for Highly Efficient Fault Diagnosis of Rotary Machines in Roll-to-Roll systems
- Author: Hyogeun Oh, Jaehyun Noh, Changbeom Joo, Gyoujin Cho, Jeongdai Jo, Changwoo Lee
- Journal: Measurement [JCR Top 17.19%]
2022. 04
- [SCI(E)] Feature Selection Algorithm Based on Density and Distance for Fault Diagnosis Applied to a Roll-to-Roll Manufacturing System
- Author: Hyogeun Oh, Yoonjae Lee, Jongsu Lee, Changbeom Joo, Changwoo Lee
- Journal: Journal of Computational Design and Engineering [JCR Top 10.87%]
