🛠 Tech Stack

💼 About This Role

You'll lead research on audio-visual avatar generation for conversational AI humans. Your mission is to push generative models in diffusion and multimodal modeling to new frontiers. You'll translate cutting-edge research into production and publish at top venues.

🎯 What You'll Do

• Lead research on audio-visual generation for avatars (Neural Avatars, Talking-Heads).
• Design models capturing verbal and non-verbal signals in conversation flow.
• Drive innovation in diffusion models, long-video generation, and audio-visual modeling.
• Translate research into production with Applied ML and engineering teams.

📋 Requirements

• PhD or equivalent research experience.
• 2-3+ years hands-on experience with generative models at scale.
• Expertise in diffusion models and efficiency techniques.
• Experience in multimodal generation (video, audio, language).

✨ Nice to Have

• Skills in 3D graphics, Gaussian splatting, or large-scale training.
• Exposure to generative AI models beyond specialty.
• Familiarity with software development best practices.

🎁 Benefits & Perks

• 🚀 Series A backed by Sequoia, Y Combinator, Scale Venture Partners.
• 🌐 Remote within US or Europe considered.
• 🏢 Office in San Francisco (hybrid) or London.

📨 Hiring Process

Estimated timeline: 3-5 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Interview· 60 min
3. 3Research Presentation· 45 min
4. 4Team Interview· 45 min
5. 5Offer· 15 min