Senior Research Engineer - Multimodal & Video Foundation Model
Job Summary
Job Description
Tether is a leader in digital finance and emerging technologies, combining blockchain infrastructure with advanced AI systems to build scalable and innovative solutions. As part of its AI model team, Tether is pushing the boundaries of multimodal intelligence, focusing on integrating video, text, and audio into powerful foundation models. The Senior Research Engineer will play a key role in advancing these technologies through research, experimentation, and production-ready implementations.
Responsibilities:
- Design and develop novel multimodal and video-based AI model architectures
- Build scalable training and inference pipelines for large-scale datasets
- Optimize data processing, model execution, and system performance
- Develop tools for preprocessing and managing multimodal datasets
- Collaborate with cross-functional teams to translate research into production
- Create benchmarking systems to evaluate model performance across tasks
Requirements:
- Bachelor’s degree in Computer Science or related field
- Strong expertise in Python and PyTorch across full ML pipelines
- Experience with large-scale datasets including text, image, audio, or video
- Hands-on experience with LLMs, vision-language models, or generative video models
- Proven research contributions with publications in top AI conferences
- Strong analytical and problem-solving skills in AI research environments
Benefits:
- Fully remote work with access to global AI research teams
- Opportunity to work on cutting-edge multimodal and video AI systems
- Exposure to large-scale distributed training environments
- Collaborative and innovation-driven culture
Join Tether to help shape the future of multimodal AI and next-generation intelligent systems.
