Remote opportunity at
SynthesiaStaff Research Scientist- Interactive Avatars
Synthesia is seeking a Staff Research Scientist to join its Interactive Avatars team in a remote capacity. Operating as an AI video platform utilized by major…
Career Tools
About This Role
Synthesia is seeking a Staff Research Scientist to join its Interactive Avatars team in a remote capacity. Operating as an AI video platform utilized by major business enterprises, the company builds proprietary generative AI technology designed to enhance visual communication and workplace skill development. In this role, the selected candidate will collaborate with a research and engineering group focused on avatar-driven, interactive video diffusion models. The position involves formulating research…
Job Description
Synthesia is seeking a Staff Research Scientist to join its Interactive Avatars team in a remote capacity. Operating as an AI video platform utilized by major business enterprises, the company builds proprietary generative AI technology designed to enhance visual communication and workplace skill development. In this role, the selected candidate will collaborate with a research and engineering group focused on avatar-driven, interactive video diffusion models.
The position involves formulating research roadmaps, improving perceptual layers for interactive agents, post-training multimodal models, and adapting diffusion techniques for conversational state and listener cues. Ideal candidates bring extensive machine learning expertise, a strong publication record, and experience leading small research teams through the entire lifecycle from concept to production. The environment emphasizes rapid iteration and turning breakthrough research directly into deployed product capabilities.
Responsibilities
- Establish the research direction and roadmap for dyadic interaction modeling, balancing long-term goals with near-term product results
- Advance state-of-the-art perceptual layers for interactive agents, covering user audio and video understanding alongside contextually relevant reactions
- Post-train multimodal models to create rich, natural dyadic interactions derived from user audio and video inputs
- Modify diffusion models to handle new conditioning signals like conversational state, turn-taking, and listener cues
- Construct robust evaluation frameworks and test suites to continuously track interaction quality
- Collaborate with the data team to define data requirements and develop high-quality datasets
- Direct and mentor a small group of researchers while guiding technical decisions across research, data, and engineering
Requirements
- Deep machine learning expertise and extensive hands-on experience with diffusion models for video or avatar generation
- Experience leading a small team of researchers and mentoring junior colleagues
- Demonstrated track record of taking research concepts through to production
- Proficiency in PyTorch and modern machine learning tooling designed for large-scale training
- Clear communication abilities regarding hypotheses, experiments, and results to influence direction across different teams
Qualifications
- Strong publication record at top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, or SIGGRAPH in relevant areas like world models, dyadic interaction, or video diffusion
- Experience with real-time or streaming generation, including autoregressive video diffusion
- Knowledge of distillation or other techniques utilized for low-latency inference
- Background in audio-driven facial, gesture, or full-body motion modeling
- Familiarity with conversational modeling aspects such as turn-taking, backchanneling, or listener-response generation
Core Skills
Benefits
- Competitive compensation package
- Hybrid work setting with optional office access in London, Zurich, or Munich, or remote work capability in Europe
- 25 days of annual leave plus public holidays
- Company culture providing the option to join regular planning sessions and socials at company hubs, along with location-dependent benefits
Frequently Asked Questions
Answers are based only on the employer’s listing; where it doesn’t say, neither do we.
Is this role remote?
Yes, this position is offered with a remote status or via a hybrid work setting with offices available in London, Zurich, or Munich.
What is the employment type?
The job posting indicates that this is a full-time position.
What salary does this position offer?
The salary is not stated in the job posting.
What qualifications are required for applicants?
Applicants must have deep machine learning expertise, extensive hands-on experience with diffusion models for video or avatar generation, prior experience leading a small research team, a track record of moving research to production, and proficiency in PyTorch.
Sample Interview Questions
AI-generated questions tailored to this specific role — a preview of the full practice set.