Summary
Overview
Work History
Education
Skills
Additional Information
Timeline
Generic

Kyung-soo Kim

AI Research Engineer
Seoul, South Korea

Summary

Knowledgeable AI Engineer with background in innovative research and development. Proven track record of contributing to significant projects and delivering impactful solutions in cutting-edge technology fields. Demonstrated ability in AI and problem-solving, utilizing advanced technical skills and cross-functional collaboration.

Overview

4
4
years of professional experience

Work History

AI Research Engineer

NCSOFT
Pangyo, Gyeonggi-do
10.2022 - Current

AI Agent for Advertising (PoC)

  • Developed and optimized Python APIs for automating product and service promotional video creation for small businesses using LangGraph.
  • Developed LLM-based APIs for video material recommendation and script generation through prompt engineering, and implemented a feedback-driven refinement loop to enhance script quality based on self-feedback.
  • Enhanced function-calling model performance via tool information data augmentation, SFT and research into efficient reasoning with reward shaping and model merging.
  • Improved internal content quality score from 3.1 to 4.4, and reduced reasoning path length by 31% while maintaining performance on BFCL and in-house evaluation sets.

Smart NPC Agent for Gaming

  • Designed a persona-specific LLM data pipeline and optimized RLHF for character-driven NPCs that guide users and deliver immersive dialogues.
  • Enhanced character persona fidelity through character boundary SFT, hierarchical PPO tuning, and reward modeling using text generation regularization to address reward hacking.
  • Developed an automated LLM evaluation pipeline with G-eval.
  • Mitigated reward hacking issues and increased G-eval persona score by 1.2 points (from 3.6 to 4.8), preparing the service with 16 distinct character personas.

RL-based Stock Trading Agent (PoC)

  • Developed a distributed RL framework that aggregates experiences from multiple workers to optimize trading agent performance, incorporating model segmentation and pre-trained market encoder freezing strategies.
  • Applied and validated the agent with real transactions at Korea Investment & Securities, achieving +16.43bp over TWAP and +15.45bp over VWAP in a one-month live trading pilot.

AI Research Engineer Intern

Hyundai Motors
Seoul, Seoul
04.2022 - 08.2022

Transfer Learning Optimization

  • Researched methods to efficiently adapt pre-trained deep learning models for defect detection in Hyundai Motor's smart factory domain.
  • Evaluated advanced transfer learning with regularization techniques and studied dynamic gradient adjustment strategies based on transferability to the target domain.
  • Applied the proposed approach to ImageNet-pretrained ResNet-50, achieving a 10.2% performance improvement over the baseline.

Graduate Researcher

SK Innovation
Seoul, Seoul
03.2021 - 03.2022

Optimization of Refinery Process Control Using Reinforcement Learning

  • Optimized SK refinery operation by implementing reinforcement learning (RL) models for critical valve control, replacing conventional PID systems.
  • Designed process-specific MDPs and applied a conservative offline RL training approach with uncertainty penalties to address real-world challenges such as action delays.
  • Achieved a 32% performance improvement over PID controllers and successfully deployed RL-based autonomous control for one week in live refinery operations.

Education

Master of Science - Artificial Intelligence

SungKyunKwan University
Suwon
04.2001 -

Bachelor of Science - Mechanical Engineering

Kyunghee University
Seoul
04.2001 -

Skills

PyTorch framework

Python programming

Natural language processing

Algorithm design

Model optimization

Machine learning

Additional Information

  • Jeongsoo Ha, Kyungsoo Kim, Yusung Kim. Dream to Generalize: Zero-shot Model-based Reinforcement Learning without Reconstruction. In Association for the Advancement of Artificial Intelligence (AAAI), 2023.
  • Kyungsoo Kim, Jeongsoo Ha, Yusung Kim. Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning, In International Joint Conference on Artificial Intelligence (IJCAI), 2022.

Timeline

AI Research Engineer

NCSOFT
10.2022 - Current

AI Research Engineer Intern

Hyundai Motors
04.2022 - 08.2022

Graduate Researcher

SK Innovation
03.2021 - 03.2022

Master of Science - Artificial Intelligence

SungKyunKwan University
04.2001 -

Bachelor of Science - Mechanical Engineering

Kyunghee University
04.2001 -
Kyung-soo KimAI Research Engineer