Cantina Labs
Research Scientist, Real-Time Video Generation
Europe +1 · Remote · Full-time · Posted Oct 13, 2026
- Location
- Europe
United States
About the job
Research and develop real-time video generation models for interactive characters, improving their visual quality, consistency, responsiveness, expression, and efficiency.
What you'll do
- Develop and evaluate streaming generation, fine-tuning, distillation, and inference optimization approaches.
- Improve character appearance, facial expression, gestures, body movement, and speech-motion alignment; identify and address data gaps and failure modes.
- Build evaluations, run experiments, and share findings to guide research priorities.
What they ask for
- Experience training or fine-tuning video or related generative models.
- Ability to learn unfamiliar methods quickly and turn ideas into useful experiments.
- Good experimental judgment, ownership, and clear communication.
AI focus
Research and development of real-time video generation for interactive characters, including streaming generation, fine-tuning, distillation, inference optimization, data development, and evaluation.
Model-written summary · the original posting is authoritative