Real-Time Video Synthesis Scientist — Remote

Bazeta; United States; Remote; USD 150,000 - 210,000; Full time

Benefits offered by this job

Competitive salary

Company equity

Medical insurance

Dental insurance

Vision insurance

Paid time off

Floating holidays

Parental leave

401(k) retirement plan

Lifestyle spending account

Job summary

Cantina Labs is seeking a Research Scientist to advance real-time video generation for interactive characters. You’ll work on models that ensure consistent appearance, expressive motion, and natural speech-to-motion synchronization across diverse identities and styles, with a focus on latency and reliability in streaming contexts.

The role offers freedom to propose directions, run experiments, and collaborate across teams while shaping the next wave of real-time social AI capabilities.

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

• Real-time and streaming generation: develop models that support responsive interaction while maintaining visual quality and consistency over time.
• Character expression and motion: explore appearance, facial expression, gesture, and body movement to form coherent characters and improve speech-motion alignment across identities and styles.
• Fine-tuning and post-training: adapt video models to new data, behaviors, and capabilities; explore training objectives and conditioning methods.

Job description

Cantina Labs is seeking a Research Scientist to advance real-time video generation for interactive characters. You’ll work on models that ensure consistent appearance, expressive motion, and natural speech-to-motion synchronization across diverse identities and styles, with a focus on latency and reliability in streaming contexts.

The role offers freedom to propose directions, run experiments, and collaborate across teams while shaping the next wave of real-time social AI capabilities.