🛠 Tech Stack

💼 About This Role

You'll lead research on advanced diffusion models for text-to-video generation, developing novel architectures and algorithms. Your work will drive improvements in visual quality and temporal consistency for our generative AI platform. You'll collaborate with cross-functional teams and contribute to top-tier publications.

🎯 What You'll Do

• Lead research on diffusion models for text-to-video generation
• Develop novel algorithms for video generation from text
• Design and run experiments to validate new ideas
• Collaborate with engineering to integrate research into production

📋 Requirements

• PhD in CS, AI, ML, or related field
• Strong publication record in top-tier AI conferences
• Experience with large-scale generative models for image/video
• Proficiency in Python and deep learning frameworks

✨ Nice to Have

• Postdoc or industrial research in generative AI for video
• Hands-on experience with text-to-video generation
• Open-source contributions in generative AI

🎁 Benefits & Perks

• 🧠 Cutting-edge research environment
• 📄 Publication opportunities at top conferences
• 🤝 Collaborative team culture
• 🏢 Bay Area location