Research Scientist, Real-Time Video Generation

The role

You will work on real-time video generation for interactive characters. This involves streaming generation, fine-tuning, distillation, inference optimization, and data development.

What you will do

• Develop models for real-time and streaming generation.
• Explore character expression and motion.
• Adapt video models to new data, behaviors, and capabilities through fine-tuning.
• Make generation faster and more efficient through distillation and inference optimization.
• Identify missing coverage and improve data curation and sampling.
• Build comparisons to make progress visible and failures understandable.
• Read relevant work, reproduce ideas, and share findings.
• Help the team decide what deserves more time and compute.

Required qualifications

• 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.

Benefits

• Competitive salary
• Generous company equity
• Medical, dental, and vision insurance – 99.99% of premiums covered by Cantina
• 42 days of paid time off, including 15 PTO days, 10 sick days, 15 company holidays, and 2 floating holidays
• Generous parental leave & fertility support
• 401(k) retirement savings plan
• $500/month lifestyle spending account
• Complimentary lunch and snacks for in-office employees
• One Medical membership

About the company

Cantina Labs is a social AI company developing a suite of advanced real-time models. Their flagship social AI platform is Cantina.