Samsung Research America (SRA) Visual Solution Lab (VSL) is looking to develop next-generation AI algorithms for display picture quality enhancement and multi-modal AI for future products by tackling real-world problems using advanced generative models.
Requirements
- Research experiences in fields like Computer Vision, Machine learning, Image Processing or any related R&D Experience with AI Technologies
- Experience with latest generative models and how to fine-tune them for different tasks
- Experience with ML frameworks such as: Pytorch, TensorFLow, Keras, etc.
- Experience in CI/CD platforms, e.g. GitHub
- Ability to address data limitation by leveraging techniques like pre-trained models, synthetic data and few-shot learning
- Experience with Scene Segmentation methods such as SAM
- Experience with AI Agents
Responsibilities
- Conduct research in advanced state-of-the-art generative models for 2D or 3D video generation from multiple modalities including but not limited to image and text using Diffusion, GANs, VAEs, Vision Transformers, VLMs …
- Design and run large scale experiments to evaluate the performance on various tasks.
- Collaborate with other colleagues and teams to develop proof of concept and demos.
- Summarize findings in top-tier journals and international conferences.
Other
- Currently enrolled in PhD in Computer Science, Computer Engineering or equivalent field of study
- Self-directed, flexible, goal oriented and strong sense of ownership
- Excellent verbal and written communications skills; experience presenting complex technical information to technical and non-technical audiences
- Experience with latest 3D representations such as Gaussian Splatting
- Experience in knowledge distillation or student teacher concepts
