Research Scientist, Interactive Avatar AI (Video Diffusion)

Synthesia; United States; Remote; USD 170,000 - 230,000; Full time

Job summary

Synthesia is seeking a Research Scientist to join our R&D team and advance avatar-centric video diffusion models. You will work on multimodal perception, real-time interaction, and model deployment to production-scale AI video agents.

You'll contribute to state-of-the-art diffusion research, publish findings, and collaborate with data engineers to build high-quality datasets and evaluation pipelines. This role offers a fast-paced, technically rigorous environment with real-world impact.

Qualifications

• A strong ML background and hands-on experience with diffusion models, ideally for video or avatar generation.
• Publications at top-tier venues (e.g., CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, SIGGRAPH) or equivalent demonstrated impact.
• Experience taking research ideas through to working implementations, and motivation to see them reach production.
• Proficiency in PyTorch and modern ML tooling for large-scale training.
• Clear communication of hypotheses, experiments, and results.

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 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.
• Run rigorous experiments, and share findings that inform the team's technical decisions.

Skills

Diffusion models

Publications

Production deployment

Large-scale training

Clear communication

Tools

PyTorch

Job description

Synthesia is seeking a Research Scientist to join our R&D team and advance avatar-centric video diffusion models. You will work on multimodal perception, real-time interaction, and model deployment to production-scale AI video agents.

You'll contribute to state-of-the-art diffusion research, publish findings, and collaborate with data engineers to build high-quality datasets and evaluation pipelines. This role offers a fast-paced, technically rigorous environment with real-world impact.