Senior Diffusion Scientist - Text-to-Video Research

We Love AI Jobs; San Francisco (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

Genmo, a research lab in San Francisco, seeks an exceptional Research Scientist to advance diffusion models for text-to-video generation. You will create novel architectures and algorithms, pushing visual quality, temporal consistency, and semantic fidelity while translating research into practical systems.

You will publish, collaborate with product and engineering teams, mentor junior researchers, and stay current with top conferences.

Qualifications

• PhD required in CS/AI or closely related field.
• Experience leading diffusion-model research for video tasks.
• Strong publication record in top conferences.
• Proficiency in Python and DL frameworks (PyTorch/TensorFlow).
• Experience with distributed computing is a plus.

Responsibilities

• Lead research on diffusion models for text-to-video generation.
• Develop and implement state-of-the-art algorithms for video generation.
• Design and run experiments to validate new ideas and measure model performance.
• Collaborate with product and engineering teams to productionize research.
• Stay current with literature and conferences; publish and open-source when possible.
• Mentor junior researchers and drive a culture of innovation.

Skills

Diffusion models

Text-to-video

PyTorch

TensorFlow

Python

Generative models

Distributed computing

Video quality metrics

Education

PhD in Computer Science

Tools

PyTorch

TensorFlow

Job description

Genmo, a research lab in San Francisco, seeks an exceptional Research Scientist to advance diffusion models for text-to-video generation. You will create novel architectures and algorithms, pushing visual quality, temporal consistency, and semantic fidelity while translating research into practical systems.

You will publish, collaborate with product and engineering teams, mentor junior researchers, and stay current with top conferences.