A bit about Cantina:
Cantina, founded by Sean Parker, is a new social platform with the most advanced AI character creator. Build, share, and interact with AI bots and your friends directly in the Cantina or across the internet.
Cantina bots are lifelike, social creatures, capable of interacting wherever humans go on the internet. Recreate yourself using powerful AI, imagine someone new, or choose from thousands of existing characters. Bots are a new media type that offer a way for creators to share infinitely scalable and personalized content experiences combined with seamless group chat across voice, video, and text.
If you're excited about the potential AI has to shape human creativity and social interactions, join us in building the future!
A bit about the role:
We are seeking talented Research Scientists to join our team, focused on advancing the capabilities of our AI-driven social platform. As a Research Scientist, you will develop advanced models for video and audio generation tailored for real-world applications, with a focus on real-time and offline human-centric video generation (currently focusing on talking heads). Our approach involves leveraging diffusion models, flow matching, and GANs, as well as optimizing neural networks and creating audio-driven avatars.
As a Research Scientist, you will:
Conduct research to develop innovative models and algorithms for image and video generation.
Publish research in open-access formats and contribute to the AI community.
Collaborate with product and design teams to implement prototypes into production.
Optimize models and improve their efficiency for real-world applications.
A bit about you:
Ph.D. or equivalent experience in Computer Science, Electrical Engineering, or related fields with a focus on generative modeling, especially in computer vision.
Experience in areas such as image/video generation, audio sequence-to-sequence modeling, model distillation, and optimization (experience in all areas is not mandatory).
Proven track record of publications at top-tier conferences or in reputable journals.
Proficiency in working with video, audio, text, and images for real-time or offline tasks.
Strong programming skills in Python and expertise with PyTorch or TensorFlow.
Why Join Cantina AI?
Opportunity to work on groundbreaking AI technologies that redefine human-computer interaction.
Collaborative and inclusive culture that values innovation, continuous learning, and professional growth.
Competitive compensation package including equity options, healthcare benefits, and flexible work arrangements.
Application Process: Please submit your resume, cover letter, and any relevant portfolio or publications demonstrating your research contributions in AI.
Location: London, England is highly preferred, but we are also open to remote in the GMT time zone.
