2026 Fall Intern, Computer Vision/AI

Samsung Research America Internship•Mountain View, CA

1d•Onsite

About The Position

Samsung AI Research Center (SAIC) in Mountain View, California, is seeking outstanding research interns for the Vision Intelligence lab. The lab focuses on long-term research with the potential to impact future Samsung products. The primary research area is multimodal understanding and generation, aiming to push the state-of-the-art in this field. Interns will collaborate with leading researchers on projects related to multimodal (image, video, 3D, text) retrieval, question answering, reasoning, generation, and editing.

Requirements

Currently pursuing a MS or PhD degree.
Experience with programming in Python, Pytorch, Transformers etc.
Previous publications in top-tier conference and journals in CV/ML/AI such as CVPR, ECCV, ICCV, ICML, NeurIPS, AAAI.
Experience in one or more of the following areas: VLMs (model architecture design, pretraining, post training - SFT, RLHF, GRPO), diffusion models and other generative AI approaches for image/video/3D domains, design and development of efficient multi-modal models (knowledge distillation, mixture of experts), Vision Language Action Models (VLA) for Agentic systems (robotics, GUI based task automation).
Strong oral and written communication skills.

Responsibilities

Conduct research on multi-modal models in areas such as multimodal retrieval, question answering, reasoning, generation, and editing.
Write maintainable code to implement research ideas.
Collaborate closely with the team to discuss findings and improve methods.
Execute experiments, document progress, and present insights.
Prepare findings for submission to a major conference or journal.