Research Scientist – Interactive Avatars

Synthesia

. Join a team of 40+ researchers and engineers in R&D working on generative AI, avatar-centric interactive video diffusion models .

Posted 10/6/2026full-timeRemoteMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

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

Demonstrates expertise in generative AI and multimodal models, with a strong focus on dyadic interaction modeling and video diffusion techniques. Proficient in building evaluation frameworks and conducting rigorous experiments to enhance interactive agent performance.

Highest-signal resume keywords

Strong ML BackgroundHands-On Experience With Diffusion ModelsProficiency In PyTorchPublications At Top-Tier VenuesExperience With Real-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 ModelsDyadic Interaction ModelingVideo GenerationLarge-Scale TrainingAutoregressive Video DiffusionLow-Latency Inference TechniquesAudio-Driven Motion ModelingConversational ModelingResearch Implementation

Soft Skills

Clear CommunicationMentoring Experience

Tools & Technologies

PyTorchModern ML Tooling

Industry Keywords

Generative AIInteractive VideoEvaluation FrameworksData Needs DefinitionTechnical Decision Making

Tech Stack

Tools & technologies

PyTorch

About the role

Key responsibilities & impact

Join a team of 40+ researchers and engineers in R&D working on generative AI, avatar-centric interactive video diffusion models
Contribute to research direction for dyadic interaction modeling and own well-scoped research problems end to end
Advance the perceptual layer of interactive agents by understanding user audio and video and generating contextually appropriate reactions
Post-train multimodal models to generate 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 evaluation frameworks and test suites for tracking interaction quality
Partner with the data team to define data needs and shape high-quality datasets
Run rigorous experiments and share findings that inform technical decisions

Requirements

What you’ll need

Strong ML background and hands-on experience with diffusion models, ideally for video or avatar generation
Publications at top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, or SIGGRAPH in world models, dyadic interaction, or video diffusion, or equivalent demonstrated impact
Experience taking research ideas through to working implementations
Proficiency in PyTorch and modern ML tooling for large-scale training
Clear communication of hypotheses, experiments, and results
Experience with real-time or streaming generation, including autoregressive video diffusion (nice to have)
Distillation or other techniques for low-latency inference (nice to have)
Audio-driven facial, gesture, or full-body motion modeling (nice to have)
Conversational modeling, such as turn-taking, backchanneling, or listener-response generation (nice to have)
Experience mentoring students or junior researchers (nice to have)
Ability to work legally in the country of employment without visa sponsorship, as indicated in the application form

Benefits

Comp & perks

Build production-scale video foundation models in a fast-growing Generative AI company
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
Highly technical, high-ownership environment where work ships