ciy405x@gmail.com / (+82) 10-9504-8680 / Seoul, South Korea / LinkedIn
Machine Learning Engineer with 4 years of experience since 2021.
Focus: 3D Deep Learning, Generative Models, Cross-Platform Systems, Performance Optimization.
Currently building production-ready 3D content generation pipelines based on diffusion and language models.
Main interest: making 3D ML models run faster, cheaper, and more useful for games, graphics, and visual applications.
- World’s first in-game 3D generation system for consumer release
→ Deployed in inZOI, enabling players to generate 3D furniture, props, and accessories from a single photo within 15 seconds
→ Ported across architectures including Intel, ARM, and Apple Silicon
→ Became the most beloved AI feature, widely shared by users (over 1 million creations): - Real-time text-to-building generation using small language models (SLM)
- ACM TOG (proc. of SIGGRAPH) paper
- Granted US patent
- Languages: Python, C++, JavaScript
- Frameworks: PyTorch, TensorFlow, ONNX
- Graphics: CUDA, OpenGL, WebGL
- Infra/Tools: Unreal Engine, Blender
- Current: ML Engineer at KRAFTON (the PUBG company), deploying AI-driven content creation pipelines
- Previous: ML Engineer at SPACEWALK, optimizing architectural design via reinforcement learning (RL)
- Education:
- MS in Computer Science, KAIST
- Thesis on Monte Carlo rendering denoising
- GPA 4.25 / 4.30
- BS in Computer Science and Mathematics, KAIST
- GPA 4.00 / 4.30
- Double major
- Dean's List (Top 3%) for 3 consecutive semesters
- Most enjoyably immersed courses: Computer Graphics, Operating Systems, Real/Complex/Numerical Analysis, Linear Algebra, Matrix Computation, 3D Machine Learning, and GPU Programming
- Advised and mentored 50 undergraduate students as a counseling assistant
- MS in Computer Science, KAIST