Tether is a leading technology company at the intersection of blockchain, AI, and global financial infrastructure. Through its innovative ecosystem, Tether develops scalable solutions that empower secure digital transactions and advanced computing capabilities. As an AI Video Research Engineer Intern, you will contribute to pioneering research in video generation and multimodal learning, helping to shape next-generation AI systems.
Responsibilities:
- Conduct research on video and multimodal video generation foundation models
- Improve open-source models through experimentation and optimization
- Explore areas such as pre-training, fine-tuning, inference, and architecture design
- Benchmark models against state-of-the-art approaches and identify limitations
- Work with large-scale video datasets and distributed GPU training systems
- Collaborate with researchers and engineers on publishable research projects
Requirements:
- MSc or PhD candidate in Computer Science, Machine Learning, or related field
- Experience in image generation, video generation, or multimodal learning
- Familiarity with open-source video foundation models and their limitations
- Proficiency in PyTorch and deep learning workflows
- Strong analytical thinking and research capabilities
- Prior publications in top-tier conferences such as CVPR, NeurIPS, or ICLR
Benefits:
- Opportunity to work on cutting-edge AI research and large-scale systems
- Collaboration with global experts in AI and blockchain technology
- Exposure to high-performance computing environments and datasets
- Potential to publish research in leading academic conferences
Join Tether to contribute to advancing the future of AI-driven video generation and multimodal technologies.