Research Scientist - Foundation Models
Krafton is seeking a Research Scientist in AI Research to pioneer new gaming experiences through advanced technologies. The role focuses on the design and development of foundation models and requires expertise in deep learning, particularly with multi-modal models. Candidates should have experience with top-tier AI/ML conferences and exhibit strong research capabilities. The position requires collaboration across diverse teams to propose innovative solutions in gaming. This is a contract position located in Seoul, South Korea, offering a unique opportunity to shape the future of gaming technology.
Job description
Overview
Krafton is pioneering the path to players' dreams. With bold imagination and breakthrough technology, we create unforgettable worlds for fans across the globe.
Team Introduction
Over the past few years, Krafton has focused on deep learning as a new challenge and area to expand our game development capabilities. We are actively investing in core talent recruitment.
AI Research Mission
Krafton's AI Research department provides AI solutions by collaborating across various fields and developing proprietary deep learning technologies. Key objectives include:
- Enhancing game production efficiency through deep learning.
- Developing CPC to enable user participation in gameplay.
Foundation Model R&D
The Foundation Model Research team researches and develops core MLLM technologies to contribute to new gaming experiences. Responsibilities include:
- Designing and building foundation models handling text, image, audio, and game logs.
- Accumulating insights on model architecture, learning algorithms, data pipelines, and evaluation.
Culture Fit
Team members thrive in a collaborative environment, exchanging creative ideas across diverse projects and backgrounds. Openness to all ideas irrespective of age or rank is encouraged, and support for language barriers is provided.
Responsibilities
As a Research Scientist, you will:
- Conduct large-scale multi-modal LLM training and precursor research.
- Enhance modeling, data, and evaluation pipelines for improved model performance.
- Present research findings at top-tier conferences such as NeurIPS, ICLR, and ICML.
Required Qualifications
- Advanced degree in deep learning or a related field, or equivalent research experience.
- Experience writing papers for top-tier AI/ML conferences.
- Ability to lead research and quickly understand and design experiments based on deep learning literature.
- Strong communication skills and valid reason for international travel.
Preferred Qualifications
- Experience presenting or winning awards at top-tier AI/ML conferences.
- Experience with training or deploying large foundation models (over 20B parameters).
Application Process
The selection process includes:
- Document screening > Preliminary interview > Technical test > Technical fit interview > Culture fit interview > Reference checks > Offer and acceptance.
Documents Needed
- CV, cover letter, career document, and portfolio are required.
Location
- Yeoksam Centerfield West Tower or Seongsu
Employment Type
- Contract (1 year, not eligible for regular conversion)
Job details
- Published
- March 5, 2026
- Last checked
- November 16, 2026
- Job source
- greenhouse
- Workplace
- On-site · Seoul, KR
- First seen
- March 5, 2026
See how well you match this job
Log in or sign up and Eva will compare your profile with this role, explain your strengths and show what to improve.
Sign up to see your matchAlready have an account? Log inMore at krafton
Similar jobs from this company
None listed.
Across the market
Similar jobs from other companies
Third-party content disclaimer
Full job descriptions are sourced directly from third-party applicant tracking systems (ATS), job boards, recruitment platforms, and employer career pages.
LiftmyCV does not claim ownership of this content or guarantee its accuracy or current availability. All original content is the intellectual property of the respective employers or other rights holders.
LiftmyCV hiring intelligence, availability checks, and related-job recommendations are generated from LiftmyCV data and public sources.
If you prefer, you may apply directly via the original listing for transparency.