Research Scientist (diffusion)
San Francisco HQ • FullTime
Posted 19d ago
Job Location
San Francisco HQ
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Research Engineer
About the job
Genmo is a research lab focused on developing advanced video world models to understand, simulate, and interact with the physical world, aiming to unlock the right brain of AGI. We are seeking an exceptional Research Scientist to pioneer cutting-edge diffusion models for text-to-video generation. This role involves creating novel architectures and algorithms to transform written descriptions into high-quality, coherent video content, pushing the boundaries of physical intelligence and enabling robots to learn and act in dynamic environments.
Responsibilities
- Lead research on advanced diffusion models for text-to-video generation, enhancing visual quality, temporal consistency, and semantic fidelity.
- Develop and implement state-of-the-art algorithms for text-to-video synthesis.
- Design and conduct experiments to validate new ideas and evaluate model performance.
- Collaborate with cross-functional teams to integrate research into production pipelines.
- Stay current with the field through literature review and conference attendance.
- Contribute to the research community via publications and open-source contributions.
- Mentor junior researchers and foster innovation.
- Align research directions with user needs and market opportunities by working with product teams.
Requirements
- Ph.D. in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
- Strong publication record in top-tier conferences (e.g., CVPR, ICCV, NeurIPS, ICML) focusing on generative models, especially diffusion models.
- Extensive experience implementing and optimizing large-scale generative models for image or video tasks.
- Deep understanding of state-of-the-art text-to-image and text-to-video generation techniques.
- Proficiency in Python and deep learning frameworks like PyTorch or TensorFlow.
- Excellent communication skills for explaining complex technical concepts.
- Proven ability to work collaboratively in a team environment.
- Postdoctoral or industrial research experience in generative AI for video is ideal.
- Hands-on experience with text-to-video generation projects is ideal.
- Expertise in other generative model architectures (e.g., GANs, VAEs) for video is ideal.
- Experience with large-scale datasets and distributed computing environments is ideal.
- Familiarity with video codecs, compression techniques, and perceptual quality metrics is ideal.
- Contributions to open-source projects in generative AI are ideal.