한국어🇰🇷English🇬🇧

Portfolio: Jeayoung Jeon

AI Platform Engineer

I’m Jeayoung Jeon [전제영], an AI Platform Engineer in Seoul. I enjoy solving problems through technology and pursue growth alongside my team. As a software engineer with 6 years of experience, with AI and clusters as my primary domain, I specialize in:

  • GenAI development: Implementing and operating GenAI workloads and AIOps platforms in cloud-native environments.
  • Team leadership: Leading collaboration, architecture, and platform engineering in teams of about ten.
  • Architecture: Building hybrid Kubernetes clusters for high performance, high availability, and GPU optimization.
  • Technical expertise: Contributing to Agentic AI, ML, DevOps decisions with backgrounds in Computer Visions and Automotives.

I’m open to new challenges in automotive, AI, and beyond. Please feel free to contact me if you have a team I can contribute to. See my resume for my background and achievements.

PDF
Email
Website
https://jyje.online
LinkedIn
LinkedIn
GitHub
Github

Work

– present (1 Year 6 Months)

Intermediate Software Engineer [책임, Professional] Hyundai AutoEver

Roles Lead AI Platform Engineer at Development Environment Platform Team, Hyundai AutoEver
  • AI/LLM Platform Developing extensible AI agents for in-house toolchains and AIOps configuration
  • Cloud-Native AI Applying k8s+AI in practice and advising team members

– (3 Years 10 Months)

Intermediate Software Engineer [선임-책임연구원] MAXST

Roles Lead MLOps/DevOps Engineer at Technology Division, MAXST
  • MLOps/AIOps Designed ML APIs and data pipelines. Built RAG+LLM systems for enterprise solutions
  • SRE Led site & service reliability engineering initiatives for web services and ML workloads
  • Infrastructure Architected hybrid clusters (AWS EKS + On-Premise) for digital twin platform
  • Algorithm Research Reviewing computer vision algorithms in state-of-art papers and implementing prototypes

– (8 Years 6 Months)

Graduate Student Researcher in Computer Vision POSTECH

Roles Ph.D Integrated Student at Department of Electrical Engineering, POSTECH
  • Computer Vision Research on hyperparameters for accurate and efficient computer vision algorithms
  • Automotives Principal computer vision technologies for autonomous driving including ADAS and SLAM; Participated in the development of the Korean government's ADAS research projects
  • FPGA Efficiently implemented computer vision and machine learning algorithms with real-time parallel matrix processing; SoC-type GPU/NPU accelerator

Projects

– present (5 Months)

Vehicle SW Verification Agentic AI Platform Hyundai AutoEver

Role Built a Deep Agents vehicle SW verification platform as an AI/MLOps Engineer
  • Deep Agents Development Developed a vehicle SW verification AI platform integrated with various toolchains using Deep Agents
  • Platform Engineering Designed a scalable agent platform architecture based on LangChain and Kubernetes
Skills: Skill Stack for Vehicle SW Verification Agentic AI Platform
  • Deep Agents
  • Platform Engineering
  • LangChain
  • Kubernetes
  • Agentic AI
  • RAG
  • MCP
  • AIOps

– (10 Months)

Codebeamer AI Assistant Hyundai AutoEver

Role Built an in-house RAG and tool-based conversational Agentic AI assistant
  • Agentic AI Development Developed conversational Agentic AI using RAG and Tools for in-house development
  • RAG Configured knowledge base with various strategic vector stores for context augmentation
  • Tool Integration Integrated and executed with Hyundai AutoEver's toolchain using MCP tools and domain-specific tools (ALM usage guidance, CBQL query debugging support)
Results AI Template Acquisition and AI Planning Direction Acquisition
  • AI Template PoC for reusable AI full stack, knowledge base, and AIOps
  • AI Planning Promoted agent productization and agent factory initiatives
Skills: Skill Stack for Codebeamer AI Assistant
  • RAG
  • LLM
  • VectorDB
  • MCP
  • Agentic AI
  • AIOps

– (10 Months)

Widearth: Digital Twin & AR Content Platform Widearth, MAXST

Role Lead ML/Infra Roles ~ MLOps/DevOps + ML Backend + SRE [contrib 75%]
  • DevOps & SRE IaC, GitOps, CI/CD Pipelines, Monitoring, Logging, Notifications, Multi-Deployment, Emergency Response
  • Hybrid Clusters Public Cloud + On-Premise Kubernetes, API Gateway Pattern, Dynamic VMs, GPU Cost Optimization
  • ML Workloads ML APIs, ML Pipelines, Data Lakes, Dockerizing, Model CI/CD
Results Service Launch ~ Small Team, Full Features, More Availability, Less Cost
  • Launch Launched and operated a platform with 15 people, 8 developers, and 1 infra engineer.
  • Low Cost Reduced cloud costs by 15M KRW (70%) by using hybrid clusters for 300+ maps.
  • Robust Infra Achieved 96% annual availability and 14-day downtime with hybrid clusters.
Skills: Skill Stack for Project Widearth
  • AWS EKS
  • Kubespray
  • Python/FastAPI
  • Argo Workflows
  • Argo CD
  • Bitbucket Pipelines
  • Karpenter

– (6 Months)

MLOps: On-Premise MLOps with Open Source Projects MAXST

Role Lead MLOps Engineer ~ Planning + VoC + PoC + ML Workloads/Infra + Operation [contrib 90%]
  • Kubeflow Integrated Argo Workflows; AutoML, Distributed Training, Model Registry; 16 GPUs Acceleration
  • JupyterHub Integrated JupyterHub with IDE; Remote GPU Notebook, 4 GPUs Acceleration
  • VectorDB Milvus, ChromaDB, RAG+LLM Chatbot
  • ML Infra Setup CI/CD, NAS, Data Lake, Image Registry for ML Workloads
Results Improved research capacity and availability through resource consolidation and automation.
  • Improved Env. Consolidated research servers on K8s to improve capacity, stability, and adoption.
  • AI Platform Expanded from 2 to 10 users and reduced technical debt through MLOps upgrades.
  • GPU Utilization Ran 800+ AutoML experiments, tripled GPU use, and commercialized the platform.
Skills: Skill Stack for On-Premise MLOps
  • Kubeflow
  • Katib
  • Training Operator
  • Model Registry
  • JupyterHub
  • Argo Workflows
  • Milvus
  • ChromaDB
  • Ollama
  • Open WebUI
  • Grafana Stack
  • TensorBoard

– (13 Months)

DevOps: Hybrid Clusters for Internal/External Projects MAXST

Role DevOps Engineer ~ Hybrid Clusters + CI/CD + Chatbot + Data Pipelines [contrib 50%]
  • Hybrid Clusters Public Cloud, On-Premise Kubernetes, Multi-Cluster, API Gateway, IaC, GPU Operator
  • CI/CD Public CI Platform, On-Premise Custom CI, GitOps CD, ChatOps for Results/Issues
  • Pipelines Data Pipelines for ML Research, Production Pipelines for ML Inference
Results Launched hybrid clusters to raise on-prem use, cut cloud costs, and spread DevOps.
  • Cost Reduction Maintained availability while cutting costs 50% versus pure cloud infrastructure.
  • Resource Utilization Used 90% of idle on-prem resources and enabled multi-cluster prototyping.
  • DevOps Culture Introduced cloud-native CI/CD, modernization, and monitoring.
Skills: Skill Stack for DevOps and Hybrid Cluster
  • Kubernetes
  • AWS EKS
  • IaC
  • Ansible
  • Terraform
  • CI/CD
  • Bitbucket Pipeline Runners
  • Argo CD
  • Argo Workflows
  • Python/FastAPI
  • Python/Bolt (Slack)

– (2 Years)

Computer Vision Engineer MAXST

Role Associate Researcher ~ Algorithm research for digital twin systems and prototyping [contrib 50%]
  • Digital Twins Digital twin system implementation using algorithms for converting perspective and 360 images to 3D space.
  • AR/XR Camera calibration and AR/XR prototype development for various smart glasses
  • Automation Development of automated pipelines for data acquisition and analysis
  • Military Service Engaged in position related to graduate school majors and performed alternative military service.
Results Development of computer vision algorithms and construction of digital twin systems
  • Digital Twins Developed Visual-SLAM and ICP algorithms for digital twin systems.
  • Automation Development of automated pipelines for data acquisition and analysis
Skills: Skill Stack for computer vision research
  • Computer Vision
  • Visual-SLAM
  • SfM
  • ICP
  • Python
  • OpenCV
  • .NET/C#
  • Unity

– (8 Years 8 Months)

Computer Vision and ADAS Researcher (Integrated Program) POSTECH

Role Graduate Student Researcher ~ Computer Vision and ADAS Research [full-time]
  • 2018-2020 Computing and Control Engineering Lab. (Prof. SH, Han)
    Digital Twins and Simultaneous Localization and Mapping (SLAM) Research
    • Visual-SLAM Research using Multiple Cameras for Autonomous Driving
    • Prototyping of Digital Twins for ADAS and SLAM
    • Virtual Visual-SLAM for Real-World Environments
  • 2012-2018 Advanced Signal Processing Lab. (Prod. H, Jeong)
    Advanced Driver Assistance Systems (ADAS) and Edge Computer Vision Research
    • High-Performance, Efficient FPGA Implementation of ADAS
    • High-Speed Algorithm Development for Traffic Signs and Road Terrain Detection
    • Research on Stereo Vision Algorithm for 3D Depth Estimation
    • Stereo Vision-based Online Calibration for Vehicle Cameras
    • Optimization Algorithm Research for Computer Vision using Cost Aggregation Table
Results Researched automotive simulation in virtual environments and edge ADAS.
  • Digital Twins Virtual Visual-SLAM for Real-World Environments
  • Edge ADAS Research of ADAS including Traffic Sign Detection & Lane Terrain Detection with FPGA
Skills: Skill Stack for Computer Vision and ADAS Research
  • Computer Vision
  • Digital Signal Processing
  • Automotives
  • Autonomous Driving
  • Advanced Driver Assistance Systems (ADAS)
  • Finite Programmable Gate Array (FPGA)
  • Traffic Sign Detection
  • Lane Terrain Detection
  • MATLAB/Simulink
  • C/C++

Skills

Highlighted items are specialized in industry-ready.

GenAI & AIOps
Keywords:
  • Public/On-Premise LLM
  • RAG
  • MCP
  • Agentic AI
MLOps
Keywords:
  • Kubeflow
  • AutoML Katib
  • Training Operator
  • JupyterHub
DevOps & SRE
Keywords:
  • Kubernetes
  • On-Premise
  • AWS EKS
  • GCP GKE
  • Hybrid Clusters
  • ARM64
  • IaC
  • Kubespray
  • Terraform
  • Ansible
  • Istio
  • Grafana Stack
  • Karpenter
CI/CD/CT/CT
Keywords:
  • Argo Projects
  • Bitbucket Pipelines
  • GitLab CI
  • GitHub Actions
  • Self-Hosted Runner
  • Kaniko
  • Buildah
  • Locust
  • Litmus
ML Backend
Keywords:
  • Python/FastAPI
  • Python/LangGraph
  • Ollama
  • Milvus
  • PostgreSQL
  • Redis
Computer Vision
Keywords:
  • Automotives
  • SLAM
  • PyTorch
  • OpenCV
  • FPGA
UI/UX
Keywords:
  • Slackbot
  • Python/FastUI
  • Open WebUI
  • Vercel AI SDK
  • .NET/MAUI
  • .NET/WPF
  • Unity
Programming languages
Keywords:
  • Python
  • .NET/C#
  • C/C++
  • MATLAB

Education

– (8 Years 6 Months)

Integrated Ph.D. Program Coursework Completed Pohang University of Science and Technology (POSTECH) 3.2/4.3

Field Electrical Engineering · Computer Vision & Signal Processing (Virtual Visual-SLAM, 2020)
Keywords Computer Vision · Digital Signal Processing · SLAM · ADAS

– (4 Years)

Bachelor's Degree Kumoh National Institute of Technology (kit) 4.3/4.5

Field Electronic Communication (Underwater LED Visible Light Communication, 2011)
Keywords Digital Signal Processing · Electronic Communication · Visible Light Communication · FPGA

Awards

🏅 Altera Design Contest 2014, Excellence Prize from Intel-Altera Korea

[System] FPGA, Vision-Based Driver Support Navigation System

🏅 Best Poster Session from KYUTECH-POSTECH Joint Workshop

[Poster] Iterative Polygon Detection using Harris Corner Space Method for Finding Traffic Signs

🥈 Altera Design Contest 2013, 2nd Prize from Intel-Altera Korea

[System] FPGA, Vision-Based Traffic Sign Recognition System

🏅 Summa Cum Laude from Kumoh National Institute of Technology

Highest Honors in Undergraduate Electronic Engineering School, 2012

🏅 NAVER Power KiN 2011 from NAVER

Knowledge Expert in `Electronics Engineering, Math and Programming`. 723 Answers, Accepted 98.1%

Publications

Full list is available on Google Scholar.

, POSTECH, Thesis (1st)

🎓 Virtual Visual-SLAM for Real-World Environments by Jeayoung Jeon

Innovative middle-out compression algorithm that changes the way we store data.

, ISVC, Advances in Visual Computing, 10th International Symposium (2nd)

📄 Cost Aggregation Table: Cost Aggregation Method Using Summed Area Table Scheme for Dense Stereo Correspondence by JeongMok Ha, Jeayoung Jeon, GiYeong Bae, SungYong Jo & Hong Jeong

, ICCAS, 14th International Conference on Control, Automation and Systems (1st)

📄 Polygonal symmetry transform for detecting rectangular traffic signs by Jea Young Jeon, JeongMok Ha, Sung Yong Jo, Gi Yeong Bae, Hong Jeong

, ICS-KIEE (1st, equivalent)

🎓 A Study on a Visible Light Communication using LED in Under-water Environment by Daehee Lee, Ki-Sung Park, Jea-Young Jeon, Yeon-Mo Yang

Other Activities

– present (2 Years)

AIOps Open Source Engineering and Operations GitHub

Highlights

jyje/hermes-agent-helm
jyje/ansible
jyje/claude-docker
jyje/cluster

– (1 Month)

AI Open Source Contribution LangChain OpenWiki

Highlights

Contributed to the OpenWiki 0.1.2 release

– (1 Month)

Beta Reader: Building AI Agents from Fundamentals to Practice Hanbit N / Hanbit Media

Highlights

Science & Technology · Reviewed and proofread Park Nayeon's IT book; wrote an endorsement

– (13 Months)

Teacher CoderDojo

Highlights

Taught programming at a free coding club for young people
Awarded 'Teacher of the Month'

Certifications

(Expired in )

🐳 KCSA: Kubernetes and Cloud Native Security Associate from Cloud Native Computing Foundation

(Expired in )

🐳 KCNA: Kubernetes and Cloud Native Associate from Cloud Native Computing Foundation

(Expired in )

🐈‍⬛ GitHub Foundations from GitHub

(Expired in )

🐙 CAPA: Certified Argo Project Associate from Cloud Native Computing Foundation

(Expired in )

🐳 CKAD: Certified Kubernetes Application Developer from Cloud Native Computing Foundation

(Expired in )

🐳 CKA: Certified Kubernetes Administrator from Cloud Native Computing Foundation

Interests

Research/Dev
Keywords:
  • Agentic RAG
  • Digital Twins
  • AMD-to-ARM Transition
  • Hybrid Clusters
  • Home Clusters
DevOps Culture
Keywords:
  • Coop First, Tech Next
  • Automate as Possible
  • Internal Development Platform

Languages

  • Korean: Fluency: Native
  • English: Fluency: Working Proficiency