Research Scientist (diffusion)

The role

This Research Scientist will develop cutting-edge diffusion models for text-to-video generation. You will create novel architectures and algorithms to transform written descriptions into video content.

What you will do

• Lead research initiatives in advanced diffusion models for text-to-video generation
• Develop and implement state-of-the-art algorithms for translating textual descriptions into dynamic video content
• Design and conduct rigorous experiments to validate new ideas and evaluate model performance
• Collaborate with cross-functional teams to integrate research breakthroughs into our production pipeline
• Stay at the cutting edge of the field by reviewing academic literature and attending top-tier conferences
• Contribute to the research community through high-quality publications and open-source contributions
• Mentor junior researchers and foster a culture of innovation
• Work closely with product teams to align research directions with user needs and market opportunities

Required qualifications

• Ph.D. in Computer Science, Artificial Intelligence, Machine Learning, or a closely related field
• Strong publication record in top-tier conferences (e.g., CVPR, ICCV, NeurIPS, ICML) with a focus on generative models, particularly diffusion models
• Extensive experience implementing and optimizing large-scale generative models for image or video tasks
• Deep understanding of state-of-the-art techniques in text-to-image and text-to-video generation
• Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow
• Excellent communication skills
• Proven ability to work collaboratively in a team environment

Nice to have

• Postdoctoral or industrial research experience in generative AI for video
• Hands-on experience with text-to-video generation projects
• Expertise in other generative model architectures (e.g., GANs, VAEs) and their applications to video
• Experience working with large-scale datasets and distributed computing environments
• Track record of successful collaboration with product teams on technology transfers
• Familiarity with video codecs, compression techniques, and perceptual quality metrics
• Contributions to open-source projects in the field of generative AI

About the company

Genmo is a research lab developing video world models to understand, simulate, and interact with the physical world. Their mission is to unlock the right brain of AGI.