PhD or equivalent research experience with 2-3+ years in generative models.
Deep expertise in diffusion models and latest efficiency techniques.
Hands-on experience in multimodal generation involving video, audio, and language.
Demonstrated innovation in long-video and/or audio generation.
Strong programming skills, especially with PyTorch and GPU workflows.
History of publishing in top-tier conferences like CVPR and NeurIPS.
Experience leading research and mentoring teams.
Responsibilities
Lead research on audio-visual generation for avatars in conversational contexts.
Design models integrating conversation flow with verbal and non-verbal cues.
Drive innovation in diffusion models and long-video generation.
Translate research findings into production-ready solutions with engineering teams.
Mentor junior researchers, establish research priorities, and publish significant findings.
Benefits
Role within a pioneering research lab focused on AI Humans.
Opportunity to shape the future of human-AI interactions.
Collaborate with a network of world-class investors and teams.
Access to cutting-edge research in generative models and AI technology.
Hybrid work environment with flexibility for remote work.
Full Job Description
The Role
We're hiring a Senior AI Researcher to lead research in audio-visual avatar generation. This role is for someone who thrives in ambiguity, has a track record of pushing generative models to new frontiers, and wants to define what human-AI interaction looks like in practice.
Your Mission
Lead research efforts on audio-visual generation for avatars (Neural Avatars, Talking-Heads), with a focus on conversational settings.
Design models that are coupled with conversation flow - capturing and generating verbal + non-verbal signals in sync.
Drive innovation in diffusion models, long-video generation, and audio-visual modeling.
Translate research into production by partnering with Applied ML and engineering.
Mentor researchers, set research directions, and publish impactful work.
You'll Bring:
A PhD or equivalent research experience, plus 2-3+ years of hands-on experience applying generative models at scale.
Expertise in diffusion models and awareness of the latest efficiency techniques.
Experience in multimodal generation - spanning video, audio, and language.
Proven innovation in long-video generation and/or audio generation.
Excellent programming skills - fluent in PyTorch and GPU-optimized workflows.
Track record of publications in top-tier venues (CVPR, NeurIPS, BMVC, ICASSP, etc.).
Experience leading research activities or mentoring teams.
Nice-to-Haves:
Skills in 3D graphics, Gaussian splatting, or large-scale training setups.
Broad exposure to generative AI models beyond your specialty.
Familiarity with software development best practices.
Location:
Preferred: San Francisco (hybrid) or London.
Remote within U.S. or Europe considered for exceptional candidates.