Staff Research Scientist – Interactive Avatars

Synthesia

. Set the research direction and roadmap for dyadic interaction modeling, balancing long-term bets with near-term product impact .

Posted 10/6/2026full-timeHybridLeadWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates deep expertise in machine learning, particularly with diffusion models for video and avatar generation, while effectively leading and mentoring research teams. Proficient in building evaluation frameworks and translating research into production-ready capabilities.

Highest-signal resume keywords

Deep ML ExpertiseDiffusion ModelsPyTorch ProficiencyTeam LeadershipReal-Time Generation

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Diffusion ModelsMultimodal ModelsConversational ModelingAudio-Driven Motion ModelingLow-Latency Inference TechniquesResearch to ProductionEvaluation FrameworksData Needs DefinitionContextual Reaction GenerationTurn-Taking Adaptation

Soft Skills

Clear CommunicationMentoringInfluencing Direction

Tools & Technologies

PyTorchModern ML Tooling

Industry Keywords

Dyadic InteractionInteractive AgentsStreaming GenerationTop-Tier Publication RecordAvatar-Centric Models

Tech Stack

Tools & technologies

PyTorch

About the role

Key responsibilities & impact

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 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 the 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
Work on avatar-centric, interactive video diffusion models and turn breakthrough research into product capabilities that ship

Requirements

What you’ll need

Deep ML expertise and extensive hands-on experience with diffusion models, ideally for video or avatar generation
Strong publication record at top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, or SIGGRAPH in areas such as world models, dyadic interaction, or video diffusion, or equivalent demonstrated impact
Experience leading a small team of researchers and mentoring junior members
Track record of taking research from idea to production
Proficiency in PyTorch and modern ML tooling for large-scale training
Clear communication of hypotheses, experiments, and results, and ability to influence direction across teams
Experience with real-time or streaming generation, including autoregressive video diffusion
Distillation or other techniques for low-latency inference
Audio-driven facial, gesture, or full-body motion modeling
Conversational modeling, such as turn-taking, backchanneling, or listener-response generation
Legally authorised to work in the country of choice without visa sponsorship

Benefits

Comp & perks

Competitive compensation
Hybrid work setting with an office in London, Amsterdam, Zurich, or Munich, or remote in Europe
25 days of annual leave + public holidays
Option to join regular planning and socials at company hubs
Other benefits depending on location