Research Scientist: Interactive Avatar AI & Diffusion

Synthesia; Zürich; On-site; CHF 120,000 - 180,000; Full time

Job summary

Synthesia in Zurich, Switzerland, is hiring a Research Scientist to join a 40+ person R&D team working on avatar-centric, interactive video diffusion models.

You will push the frontier of machine learning for conversational agents, building models that listen, respond, and react with natural turn-taking, gaze, and motion. The role emphasizes publishing and turning research into production, collaborating with data and engineering teams.

Qualifications

• PhD in ML/CS or equivalent
• Strong publications in top venues (CVPR, ICCV, NeurIPS, ICML, ICLR, SIGGRAPH) or demonstrated impact
• Experience taking research ideas through to working implementations and production

Responsibilities

• Contribute to the research direction for dyadic interaction modeling, and own well-scoped research problems end to end.
• Advance the perceptual layer of interactive agents, including understanding user audio/video and generating contextually appropriate reactions.
• 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 and listener cues.
• Build robust evaluation frameworks and test suites for continuous tracking of interaction quality.
• Partner with data team to define data needs and shape high-quality datasets.
• Run rigorous experiments, and share findings that inform the team's technical decisions.

Skills

Diffusion models

Video generation

PyTorch

Research leadership

Publication track record

Education

PhD in ML/CS

Tools

PyTorch

CUDA

ML tooling

Job description

Synthesia in Zurich, Switzerland, is hiring a Research Scientist to join a 40+ person R&D team working on avatar-centric, interactive video diffusion models.

You will push the frontier of machine learning for conversational agents, building models that listen, respond, and react with natural turn-taking, gaze, and motion. The role emphasizes publishing and turning research into production, collaborating with data and engineering teams.