AI Researcher (Multimodal Audio/Video Generation) jobs in United States
cer-icon
Apply on Employer Site
company-logo

Tavus · 3 months ago

AI Researcher (Multimodal Audio/Video Generation)

positionSan Francisco
timeFull-time
remoteOnsite
seniorityMid, Senior Level

Tavus is a research lab pioneering human computing, focused on building AI Humans that facilitate meaningful interactions between people and machines. The AI Researcher will be responsible for researching and developing audio-visual generation models for conversational agents, collaborating with the Applied ML team to bring innovations into production.

Artificial Intelligence (AI)Developer PlatformGenerative AISoftwareVideo
check
H1B Sponsor Likelynote

Responsibilities

Research and develop audio-visual generation models for conversational agents (e.g. Neural Avatars, Talking-Heads)
Focus on models that are tightly coupled with conversation flow, ensuring verbal and non-verbal signals work seamlessly together
Experiment with diffusion models (DDPMs, LDMs, etc.), long-video generation, and audio generation
Collaborate with the Applied ML team to bring your research into real-world production
Stay ahead of the latest advancements in multimodal generation — and help shape the next wave

Qualification

Audio-visual generation modelsGenerative modelingDiffusion modelsPyTorchVideo-language models3D graphicsLarge-scale training setupsRapid prototypingSoftware engineering best practicesPublications in top-tier venues

Required

A PhD (or near completion) in a relevant field, or equivalent hands-on research experience
Experience applying image/video generation models in practice
Strong foundations in generative modeling and rapid prototyping
Deep familiarity with diffusion models, including recent advances in efficiency
Good understanding of video-language models and multimodal generation
Proficiency in PyTorch and GPU-based inference

Preferred

Experience with long-video or audio generation
Skills in 3D graphics, Gaussian splatting, or large-scale training setups
Broader exposure to generative models and rendering
Familiarity with software engineering best practices
Publications in top-tier or respected venues (CVPR, NeurIPS, BMVC, ICASSP, etc.)

Company

Tavus

twittertwittertwitter
company-logo
Tavus develops AI humans that remember and empathize, enabling seamless transitions across chat, voice, and video.
dateFounded in 2020
location
San Francisco, California, USA
people-size51-200 employees
web-link
https://www.tavus.io

H1B Sponsorship

Tavus has a track record of offering H1B sponsorships. Please note that this does not guarantee sponsorship for this specific role. Below presents additional info for your reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2025 (6)

Funding

Current Stage
Growth Stage
Total Funding
$64.22M
Key Investors
CRVScale Venture PartnersSequoia Capital
2025-11-12Series B· $40M
2023-08-29Series A· $18M
2023-03-20Seed· $6.1M

Leadership Team

leader-logo
Hassaan Raza
Co-Founder / CEO
linkedin
leader-logo
Quinn Favret
Co-Founder, COO
linkedin

Recent News

Business Wire
Tavus Announces AI Santa 2.0: The World’s First Emotionally Intelligent Holiday PAL
2025-12-10
TechCrunch
AI startup Tavus founder says users talk to its AI Santa ‘for hours’ per day
2025-12-10
Sourcery
CEO Bezos, Alex Karp, Elad Gil
2025-11-21
Company data provided by crunchbase