Research Scientist - Interactive Avatars
Synthesia is an active London-based enterprise AI video platform that lets businesses create, localize, manage, and publish videos using AI avatars and voiceovers.
Funding history
About Synthesia
Synthesia Limited provides browser-based AI video creation for business communications, training, sales enablement, marketing, and support. Its platform includes AI-assisted creation, avatars, voiceovers, translation/localization, collaboration, and publishing workflows.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will research and develop multimodal diffusion models for interactive avatars. You will model user audio and video, generate natural reactions, adapt models to conversational signals, build evaluation frameworks, define data needs, and run experiments that guide technical decisions.
Requirements
- Strong machine learning background
- Hands-on experience with diffusion models
- Publications at top-tier research venues or equivalent demonstrated impact
- Experience taking research ideas to working implementations
- Proficiency in PyTorch and modern machine learning tooling for large-scale training
- Clear communication of hypotheses, experiments, and results
Responsibilities
- Contribute to the research direction for dyadic interaction modeling
- Own well-scoped research problems end to end
- Advance perceptual modeling for interactive agents
- Post-train multimodal models for natural dyadic interactions
- Adapt diffusion models to conversational conditioning signals
- Build evaluation frameworks and test suites
- Define data needs and shape high-quality datasets
- Run rigorous experiments and share findings