Deep ML expertise and extensive hands-on experience with diffusion models, ideally for video or avatar generation.
A strong publication record at top-tier venues (e.g., CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, 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.
A 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 the ability to influence direction across teams.
Nice to have:
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.
What you'll be doing:
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 new 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 our 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.
Perks and Benefits:
Competitive compensation
Hybrid work setting with an office in London, Amsterdam, Zurich, Munich, or remote in Europe.
25 days of annual leave + public holidays
Great company culture with the option to join regular planning and socials at our hubs