About KRAFTON AI Research Division
KRAFTON AI Research Division collaborates with various internal and external fields to provide AI solutions for diverse problems and develops our own services through deep learning technology research. Our direction largely consists of two goals:
- Increasing game production efficiency and universality through the development of deep learning technology that can assist in game creation.
- Developing unique deep learning technologies and applying them to various applications inside and outside of games.
About Our Team (Project)
The AI Companion Team at KRAFTON develops AI Companions that apply LLM, SLM, and VLM in KRAFTON's internal games to interact with users, strategize, and cooperate.
- Our goal is to provide an immersive gameplay experience where AI agents work as a team with players in real-time game environments.
- We aim to help users adapt stably by understanding game situations independently and providing proactive guidance.
- We lead the entire process from optimized model design to operation.
Culture Fit
Members of the AI Research Division are not confined to their own fields but interact and collaborate with team members from different projects to propose creative ideas for various problems. Our team is composed of individuals from diverse cultural backgrounds, and we actively support methods to resolve language barriers for lively communication.
Our Mission
As a Research Engineer - Vision Language Action Game Agent, you will be responsible for:
- Researching and implementing VLA agent models that receive multimodal input (screen/text/game state, etc.) in a game environment and output actions.
- Designing data, establishing learning recipes, and analyzing and improving failure cases to enhance instruction-following performance.
- Optimizing modeling/inference/serving and verifying performance, considering real-time constraints.
- Building and operating large-scale learning data collection and refinement pipelines.
Required Experience
- Currently pursuing a Master's or Ph.D. in Artificial Intelligence (AI), Computer Science, or a related technical field.
- Ability to lead research, quickly understand deep learning-related papers, and design experiments.
- Ability to quickly adapt to new domains.
- Excellent communication skills for smooth collaboration.
Preferred Experience
- Experience in writing papers for top-tier AI/ML conferences (NeurIPS, ICLR, ICML, etc.) or top-tier journals in related fields.
- Outstanding project achievements related to Vision Language Action Models.
- Excellent communication skills with other job functions (game planning, art, business, etc.).
Employment Type
- Internship (6 months)