Research Scientist - Interactive Avatars
Remote • Europe • FullTime
Posted 10h ago
About the job
Synthesia is seeking a Research Scientist to join their R&D department, focusing on the frontier of generative AI, specifically avatar-centric, interactive video diffusion models. This role offers a unique opportunity to shape the future of AI video agents capable of natural, real-time conversations, understanding user input, and responding with human-like reactions. The team operates in a fast-paced environment, translating breakthrough research into tangible product capabilities.
Responsibilities
- Contribute to research direction and own research problems in dyadic interaction modeling.
- Advance the state of the art in the perceptual layer of interactive agents, including understanding and generating reactions from user audio and video.
- Post-train multimodal models for natural dyadic interactions.
- Adapt diffusion models to new conditioning signals like conversational state and turn-taking.
- Build robust evaluation frameworks for interaction quality.
- Define data needs and shape high-quality datasets with the data team.
- Run rigorous experiments and share findings to inform technical decisions.
Requirements
- Strong ML background with hands-on experience in diffusion models, preferably for video or avatar generation.
- Publications at top-tier venues in relevant AI fields or equivalent demonstrated impact.
- Experience translating research ideas into working implementations and a motivation to see them reach production.
- Proficiency in PyTorch and modern ML tooling for large-scale training.
- Clear communication of hypotheses, experiments, and results.
Benefits
- Build production-scale video foundation models.
- Work on human-centric video generation with real-world impact.
- Tackle hard problems in scaling, stability, and controllability.
- Influence the direction of next-generation synthetic human technology.
- Join a highly technical, high-ownership environment where your work ships.