Tether is hiring an AI Video Research Engineer Intern to work on advanced video generation and multimodal video foundation models. This remote internship is open to MSc and PhD candidates worldwide interested in cutting-edge AI research.
Key Responsibilities:
- Research and improve open-source video and multimodal video generation models.
- Work on areas such as pre-training, fine-tuning, model architecture, inference, and evaluation.
- Benchmark models against state-of-the-art systems and propose improvements.
- Work with large-scale video datasets and distributed training systems.
-
Collaborate with researchers on projects with potential for publication in top AI conferences.
Requirements:
- MSc or PhD candidate in Computer Science, Machine Learning, Computer Vision, or related field.
- Experience in image/video generation or multimodal learning.
- Proficiency in Python, PyTorch, and modern deep learning workflows.
-
Strong analytical, research, and collaboration skills.
Preferred:
Experience with diffusion or transformer-based video models, distributed training, and published research in conferences such as CVPR, ICCV, NeurIPS, or ICLR.
What You’ll Get:
- Flexible remote work environment.
- Professional development and research opportunities.
-
The chance to contribute to cutting-edge AI research and open-source innovation.