Staff Research Scientist - Interactive Avatars

About the role

As a Staff Research Scientist, you will join a team of over 40 researchers and engineers to work on the frontier of generative AI with a focus on avatar-centric, interactive video diffusion models. You will lead research initiatives to build models that hold natural, real-time conversations, enabling AI agents to understand and react to users like humans. This role involves setting research roadmaps, mentoring team members, and bridging the gap between breakthrough research and product capabilities.

Responsibilities

• 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 understanding user audio and video and generating contextually appropriate reactions.
• Post-train multimodal models to generate rich, natural dyadic interactions from user audio and 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 our 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.

Required skills

• Machine Learning
• Diffusion models
• Video generation
• Avatar generation
• PyTorch
• Large-scale training

Nice to have

• Real-time generation
• Streaming generation
• Autoregressive video diffusion
• Distillation
• Low-latency inference
• Audio-driven motion modeling
• Conversational modeling

Qualifications

• Strong publication record at top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, or SIGGRAPH
• Experience leading a small team of researchers and mentoring junior members
• Track record of taking research from idea to production

Benefits

• Competitive compensation
• 25 days of annual leave
• Public holidays

About the Company

Synthesia is the world’s leading AI video platform for business, used by over 90% of the Fortune 100. Founded in 2017, the company develops products to enhance visual communication and enterprise skill development using proprietary AI technology.