Staff Research Scientist — Generative AI & Avatar Tech

Synthesia; United States; Hybrid; USD 180,000 - 280,000; Full time

Benefits offered by this job

Hybrid work

Office in London

Office in Zurich

Office in Munich

Remote in Europe

25 days annual leave

Job summary

Synthesia is seeking a Staff Research Scientist to join our Interactive Avatars team, advancing dyadic interaction modeling and diffusion-based video agents.

You will lead a small team of researchers, set the research roadmap, mentor teammates, and collaborate with data and engineering to ship product capabilities that listen, respond, and react in real time. This is a fast-paced, high-impact role.

Qualifications

• Deep ML expertise with diffusion models, ideally for video or avatar generation.
• Strong publication record at top venues in areas like world models, dyadic interaction, or video diffusion.

Responsibilities

• Set the research direction and roadmap for dyadic interaction modeling.
• Advance state of the art in perceptual layers of interactive agents.
• Post-train multimodal models to generate rich interactions from audio and video inputs.
• Adapt diffusion models to new conditioning signals such as conversational state and listener cues.
• Build robust evaluation frameworks and test suites for ongoing interaction quality.
• Partner with data teams to define data needs and shape high-quality datasets.
• Lead and mentor a small team of researchers and drive cross-team technical decisions.

Skills

Diffusion models

Video generation

Leadership

PyTorch

Research to production

Communication

Tools

PyTorch

Job description

Synthesia is seeking a Staff Research Scientist to join our Interactive Avatars team, advancing dyadic interaction modeling and diffusion-based video agents.

You will lead a small team of researchers, set the research roadmap, mentor teammates, and collaborate with data and engineering to ship product capabilities that listen, respond, and react in real time. This is a fast-paced, high-impact role.