Beomjin Seo

AI Engineer · Seoul, South Korea

I'm currently an LLM/VLM engineer at Samsung Research, where I develop on-device AI models for Samsung smartphones used by millions of people worldwide. My work focuses primarily on the pre/post-training of VLMs, with an emphasis on hardware-friendly & efficient architectures and RL-based post-training methods.

Recently my research interests include:

  • RL-based methods and environment expansion
    To deploy physical AI models on the real world via moving beyond the fish-tank (from VLM to VLA).
  • Agentic / Continual Learning
    Giving models access to tools and operating systems, and enabling them to continually learn from their interactions and experiences.
  • Multimodal Model Training
    How to make models integrate information across modalities and make decisions based on the right evidence.
  • Hardware-friendly model architectures
    How to improve prefill/decode performance under specific hardware constraints.

Please feel free to reach out, whether you'd like to talk research or just have a casual chat!

Work Experience

Samsung Research — Full time

AI Core Team · Engineer

Jul 2022 – Present
  • Developing LLM/VLMs for devices: trained VLMs from scratch, from pre-training to post-training, to serve on-device AI models on Samsung devices. Mainly focused on pre-training. (efficient architecture search and training algorithms).
  • Developing LLMs for cloud services: trained LLMs from scratch, from pre-training to post-training, to serve LLMs for Samsung Electronic workers. Mainly focused on post-training and evaluations. (synthetic-data generation pipelines, data-mix strategies and evaluation of several perspectives)
  • Semantic Deep Search for TV manuals: prepared domain-specific datasets, trained task-specific deep-search models, and compressed model weights.

Kim Jaechul Graduate School of AI at KAIST — Intern

Research Intern, Edward's Lab (mentor: Prof. Edward Choi)

Jul 2021 – Aug 2021
  • Developed a multimodal dataset from Wikipedia and ran a proof-of-concept with it.

KIST Europe — Intern

Research Intern, Smart Convergence Group (mentor: Dr. Sangrak Lim) · Saarbrücken, Germany

Feb 2020 – Aug 2020
  • Worked on QSAR model development and molecular docking using graph attentional network models.

Education

Kyung Hee University

B.S. in Software Convergence & Biomedical Engineering · GPA 4.1 / 4.5

Mar 2015 – Feb 2022