Staff Research Scientist (Generative AI, Avatar-Centric Video Diffusion Models) at Synthesia

About the Role

As a Staff Research Scientist, you will join a team of 40+ researchers and engineers in Synthesia’s R&D department, pioneering generative AI with a focus on avatar-centric, interactive video diffusion models. This is a unique opportunity for experts in machine learning and diffusion models to shape the future of AI video agents that listen, respond, and react like humans.

You’ll build models capable of holding natural, real-time conversations, understanding user input (audio and video) and generating contextually appropriate reactions, including turn-taking, backchannels, gaze, and facial/body movements. The team moves fast, iterates often, and translates breakthrough research into product capabilities that ship.

What You’ll Do

• Set the research direction and roadmap for dyadic interaction modeling, balancing long-term bets with near-term product impact.

• Advance the state of the art in the perceptual layer of interactive agents, including user audio/video understanding and contextually appropriate reaction generation.

• Post-train multimodal models to generate rich, natural dyadic interactions from user audio/video inputs.

• Adapt diffusion models to new conditioning signals, such as conversational state, turn-taking, and listener cues.

• Build robust evaluation frameworks and test suites for continuous tracking of interaction quality.

• Partner with the data team to define data needs and shape high-quality datasets.

• Lead and mentor a small group of researchers, and drive technical decisions across research, data, and engineering.

What We’re Looking For

• Deep ML expertise and extensive hands-on experience with diffusion models, ideally for video or avatar generation.

• A strong publication record at top-tier venues (e.g., CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, SIGGRAPH) in areas such as world models, dyadic interaction, or video diffusion, or equivalent demonstrated impact.

• Experience leading a small team of researchers and mentoring junior members.

• A track record of taking research from idea to production.

• Proficiency in PyTorch and modern ML tooling for large-scale training.

• Clear communication of hypotheses, experiments, and results, and the ability to influence direction across teams.

Nice to Have

• Experience with real-time or streaming generation, including autoregressive video diffusion.

• Distillation or other techniques for low-latency inference.

• Audio-driven facial, gesture, or full-body motion modeling.

• Conversational modeling, such as turn-taking, backchanneling, or listener-response generation.

Why Join Us?

We’re living the golden age of AI. The next decade will yield the next iconic companies, and we dare to say we have what it takes to become one.

Our Culture

At Synthesia, we’re passionate about building, not talking, planning, or politicizing. We hire the smartest, kindest, and most unrelenting people and empower them to do their best work without distractions.

Serving 50,000+ Customers (and 50% of the Fortune 500)

We’re trusted by leading brands such as Heineken, Zoom, Xerox, and McDonald’s.

Proprietary AI Technology

Since 2017, we’ve been pioneering advancements in Generative AI. Our AI technology is built in-house by a team of world-class AI researchers and engineers.

AI Safety, Ethics, and Security

AI safety, ethics, and security are fundamental to our mission. Our position is clear: People first. Always.

The Good Stuff...

• Competitive compensation

• Hybrid work setting with an office in London, Amsterdam, Zurich, Munich, or remote in Europe.

• 25 days of annual leave + public holidays

• Great company culture with regular planning and social events at our hubs.

• Other benefits depending on your location.