Real-Time Video Generation Scientist

Cantina Labs; United States; Remote; USD 180,000 - 260,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

401(k) retirement savings plan

Generous parental leave & fertility

Lunch and snacks in-office

One Medical membership

Company equity

Job summary

Cantina Labs is seeking a researcher to advance real-time video generation for interactive characters. You will work across streaming generation, fine-tuning, distillation, and inference optimization, shaping models that feel present in conversations and stories.

You’ll explore latency, motion, and the alignment of speech with movement, contributing to a fast, reliable generation pipeline and publishing early results with the team.

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.

Responsibilities

• Develop models for real-time video generation and streaming.
• Fine-tune and distill video models for performance and efficiency.
• Collaborate with research and engineering to evaluate approaches and share results.

Skills

Video generation

Experiment design

Communication

Job description

Cantina Labs is seeking a researcher to advance real-time video generation for interactive characters. You will work across streaming generation, fine-tuning, distillation, and inference optimization, shaping models that feel present in conversations and stories.

You’ll explore latency, motion, and the alignment of speech with movement, contributing to a fast, reliable generation pipeline and publishing early results with the team.