Latest AI JobsBrowse Jobs
Tavus logo

AI Researcher (Multimodal Audio/Video Generation)

TavusSan FranciscoEngineering, Product, & Design
Apply on company site
Salary
Not listed
Job type
Full-time
Posted
15 May 2026
Status
Open · checked 7d ago

About this role

Role Overview

Tavus is seeking a Senior AI Researcher to drive innovation in audio-visual avatar generation at their San Francisco office. This full-time position is ideal for an experienced professional with a strong background in generative models and conversational AI systems. Candidates can also work from London or remotely within the United States or Europe under specific conditions.

Key Responsibilities

Lead research initiatives centered on audio-visual generation for talking-head models and neural avatars within conversational environments.
Architect models integrated with conversational flow to simultaneously generate and capture verbal and non-verbal signals.
Advance technological limits in audio-visual modeling, long-video generation, and diffusion models.
Collaborate closely with engineering and applied machine learning teams to move research directly into production.
Guide team members, determine research trajectories, and publish influential academic work.

Requirements

Hold a PhD or possess equivalent research experience, alongside three or more years of practical experience deploying generative models at scale.
Demonstrate deep knowledge of diffusion models and familiarity with modern efficiency methods.
Bring proven expertise in multimodal generation covering video, language, and audio domains.
Show a documented history of innovation in audio generation or long-video generation.
Exhibit advanced programming capabilities with fluency in PyTorch and GPU-optimized workflows.
Maintain a publication record in premier venues like NeurIPS, CVPR, ICASSP, or BMVC.
Possess past experience directing research projects or mentoring junior team members.

Nice to Have

Proficiency in 3D graphics, Gaussian splatting, or large-scale training architectures.
Wide-ranging exposure to generative artificial intelligence technologies outside a primary specialization.
Knowledge of standard software development best practices.

Skills and Tools

PyTorch
GPU-optimized workflows
Diffusion models
Multimodal audio, video, and language generation
Long-video generation
3D graphics and Gaussian splatting

About the Company

Tavus operates as a research lab backed by investors such as Y Combinator, Sequoia Capital, and Scale Venture Partners. The organization builds AI Humans designed to bridge the gap between people and machines through real-time human simulation models.

How to Apply

Interested candidates should visit the official Tavus careers page to submit an application for this role.

Skills and tech stack

PyTorch

Questions candidates ask

What is the location of the AI Researcher position at Tavus?

The preferred location is hybrid in San Francisco or London, with remote options considered within the U.S. or Europe for exceptional candidates.

What level of experience is required for this role?

Candidates must have a PhD or equivalent research experience, plus 3+ years of hands-on experience applying generative models at scale.

What technical skills are mandatory for the applicant?

Applicants must be fluent in PyTorch and GPU-optimized workflows, with expertise in diffusion models and multimodal generation.

What background does Tavus have as a company?

Tavus is a Series A research lab backed by investors including Sequoia Capital, Y Combinator, and Scale Venture Partners.

How should I apply for this job?

Candidates can apply directly on the official Tavus company careers page.

Ready to apply?

The application is on the official Tavus careers page.

Apply on company site