[AI Research Div.] Research Scientist - World Action Models (2년 이상 / 계약직)
Salary not listed • Seoul; Seoul, South Korea • Contract
Posted 5d ago
Remote Work Policy
On-site
Employment Type
Contract
Categories
AI Research Engineer
About the job
We are seeking a Research Scientist to join our AI Research division, focusing on World Action Models. This role involves pioneering new paths in game development through bold imagination and breakthrough technology to create unforgettable worlds for fans. Our AI Research division is dedicated to developing proprietary AI core technologies for both gaming and non-gaming sectors, enhancing existing business competitiveness, supporting AI technology commercialization, and creating new value and innovation. We aim to implement intelligent agents that interact naturally with humans and the real world by researching and developing next-generation AI core technologies such as Multimodal Foundation Models and AI Agents. We also focus on applying AI technologies to game development, services, and various industries to drive production innovation, create new user experiences, and generate AI-based service and business opportunities.
Responsibilities
- Develop MLLM from scratch, analyzing and reproducing key VLM architectures and training recipes, and designing and executing a three-stage training pipeline (visual alignment, pre-training, physical SFT) based on proprietary LLMs.
- Develop flow-matching based video/action generators.
- Research World Model pre-training using game engine data (PUBG, Enjoy, etc.) and real-world data to learn domain-independent universal physics representations, comparing and verifying pixel-space and latent-space representation methods.
- Perform task-aware post-training on completed models for specific tasks and verify actual performance through RL (e.g., ReinFlow) and simulation-based learning.
- Establish an evaluation system by designing a closed-loop evaluation framework and benchmarks to enable rapid iteration of model improvement cycles.
- Design and execute distributed training in a large-scale GPU cluster environment.
Requirements
- Master's or Ph.D. degree in a related field of Artificial Intelligence or equivalent research experience.
- Ability to lead research, quickly understand deep learning papers, and design experiments.
- Ability to adapt quickly to new domains.
- Effective communication skills for smooth work collaboration.
- No disqualifications for overseas business trips.