As a Research Engineer at Tavus, you will architect and train the video diffusion models powering our real-time facial rendering pipeline. Working under the leadership of Ioannis Patras, you’ll bridge the gap between cutting-edge research and production, shipping models that achieve emotionally accurate expressions with sub-second latency for global enterprises.
Research Engineer at Tavus
We're looking for Research Engineers with hands-on video diffusion expertise to architect and train the Phoenix-4 model, enabling emotionally accurate facial rendering with sub-second latency. If you want to see your research move from training loops to production platforms used by global enterprises, this is the role for you. Work alongside world-class experts in a flexible, remote-friendly environment while solving high-impact neural rendering problems.
Want to apply for this role?
Jack finds you jobs at companies like Tavus. Talk to Jack to get considered for roles that fit what you're great at.
Location
Remote
Compensation
Not Disclosed
Company
Tavus
Role overview
Tavus is a $64M Series B AI research lab backed by Sequoia, CRV, and Y Combinator, building real-time AI humans. Headquartered in San Francisco with a global research presence, Tavus develops the Phoenix-4 model to power conversational video interfaces that see, hear, and respond with human-like presence.
What you will do
- Design and implement novel architectures for video diffusion and flow-matching models specifically for high-fidelity facial generation.
- Develop and optimize large-scale training loops to advance the capabilities of the Phoenix-4 model for emotionally accurate rendering.
- Ship high-performance models to production, ensuring sub-second inference latency for real-time conversational video interfaces.
Who this is a fit for
- Demonstrates hands-on experience building, training, and scaling diffusion or flow-matching models specifically for video or facial synthesis.
- Possesses strong research engineering skills with the ability to implement complex neural architectures and manage large-scale training data.
- Brings broader knowledge of neural rendering techniques such as Gaussian Splatting, NeRFs, or advanced face synthesis methods.
Why this role is remarkable
- Join a well-funded Series B lab backed by premier investors like Sequoia and CRV to define the future of conversational AI.
- See your research reach production immediately through Tavus’s platform, powering real-time face-to-face AI interactions for major companies.
- Work alongside world-class experts like Head of Research Ioannis Patras in a high-impact, globally distributed research environment.
How Jack & Jill work together
I get to know what you’re great at, then find roles you’d never find yourself.Ok, I'll go first. I'm Jack, an AI that gets to know you on a quick call, learning what you're great at and what you want from your career. Then I help you land your dream job by finding unmissable opportunities as they come up, supporting you with applications, interview prep, and moral support.
I recruit from Jack’s network and make the intro when I spot a great match.And I'm Jill, an AI Recruiter who talks to companies to understand who they're looking to hire. Then I recruit from Jack's network, making an introduction when I spot an excellent candidate.
Jack gets to know what you're great at and what you want next, then searches 15 million jobs daily and helps you discover roles at companies like this.
Meet Jack
What happens next?
Jack’s an AI agent for job searching and career coaching. He works for you.
Jill is the AI recruiter working for the company. She recruits from Jack’s network.
If your profile’s a match and Tavus wants to meet, Jill will make the intro. In the meantime, Jack will send you excellent alternatives.