I am an AI Research Engineer at Gractor, where I design and deploy computer vision systems for smart city infrastructure. Before that, I spent two years as a researcher at the Pattern Recognition & ML Lab at Korea University (MSc in AI, 2023–25), advised by Prof. Seong-Whan Lee, publishing first-author papers and filing an autonomous driving patent. I started my career as a software engineer at GliTech, shipping 10+ production projects and leading STEM education initiatives.
My work spans the full stack of AI—from research (semi-supervised segmentation, adversarial robustness, depth estimation) to engineering (real-time inference pipelines, edge deployment, production ML systems) to product delivery (full-cycle project management, cross-functional collaboration, stakeholder engagement).
Tackled boundary blur and confirmation bias using confidence-weighted pseudo-labels, dynamic thresholding, and a boundary-aware module. Achieves 65.9% mIoU on Cityscapes with only 100 labeled images.
Introduced fuzzy pseudo-labeling, entropy-based weighting, adaptive class rebalancing, and lightweight contrastive regularization to improve generalization in semi-supervised semantic segmentation.
Studied stealthy backdoor triggers in CLIP-style models by aligning visual and textual embeddings in the joint representation space.
Crafted targeted perturbations for multi-label classifiers that exploit semantic label co-occurrence dependencies.
Systematic evaluation of weak-to-strong consistency and self-training techniques that served as the foundation for CW-BASS and FARCLUSS.
Depth estimation and point cloud generation for autonomous driving applications using Depth Anything V2, with an improved depth-to-pointcloud pipeline.
Multi-branch hash tables and NeRF-style encoding for large-scale dynamic urban scene reconstruction.
Bi-GRU with self-attention for classifying emotions from audio and text signals.
Comparative study of autoregressive, controllable, and diffusion-based approaches to text-conditioned image generation.
Automatic SAM prompting with a reinforcement learning agent for diverse segmentation tasks.
Integrating external APIs into reward models for more accurate and transparent decision processes.
Second-order functional connectivity embedding with domain adaptation for autism detection across diverse clinical sites.
Mutual correction framework for refining medical segmentation masks and mitigating confirmation bias with limited annotations.
Investigated the gap between declared and effective context length in LLMs, analyzing positional-encoding biases and the STRING shifting method.
AI-powered crop disease identification with severity scoring, 6 structured learning modules, community data contributions, and downloadable agricultural datasets. Built with React, TypeScript, Express, and Prisma.
20+ subjects, 70+ lessons, progress tracking with study streaks, learning analytics dashboard, and personalized settings. Built with React, TypeScript, Express, and Prisma.
Edge AI-based real-time traffic monitoring with Three.js 3D visualization, predictive analytics, and smart city integration. Built with React, TypeScript, Three.js, and FastAPI.
AI Research Engineer
Gractor · Seoul, Korea
Sept 2025 – present
ML Research Engineer
Pattern Recognition & ML Lab, Korea University · Seoul, Korea
Aug 2023 – Aug 2025
Software & AI Engineer
GliT · Hybrid
Jan 2019 – Jan 2021
Korea University
Master of Science, Artificial Intelligence
2023 – 2025
Advisor: Prof. Seong-Whan Lee · Global Korea Scholarship
Template based on Jon Barron's website.