5 months ago
Responsibilities
- Develop novel machine learning techniques for visual generative modeling.
- Implement and experiment with diffusion models, GANs, and transformer architectures.
- Optimize model performance and scaling capabilities.
- Help ensure safe and robust model deployment.
- Collaborate with cross-functional teams to integrate research innovations.
- Participate in research discussions and contribute to technical documentation.
Requirements
- BS or MS in Computer Science, Machine Learning, or a related field; recent graduates are welcome.
- At least 2 years of machine learning experience.
- Strong foundation in machine learning, particularly generative models.
- Solid programming skills in Python and PyTorch or TensorFlow.
- Experience with deep learning frameworks and model training.
- Understanding of computer vision and generative AI fundamentals.
- Academic or personal project experience with generative models.
- Clear communication skills and ability to work in a research team.
- Preferred: research projects or thesis work in generative AI.
- Preferred: experience with diffusion models, GANs, transformer architectures, and large language models.
- Preferred: familiarity with distributed computing and GPU optimization.
- Preferred: contributions to open-source machine learning projects.
- Preferred: academic publications or workshop papers.
- Preferred: experience with machine learning infrastructure and deployment.
Benefits
- Onsite role in the San Francisco office, 4–5 days per week.
Categories
AI ResearchML Engineering
About Genmo
Genmo builds AI models and tools for video generation and editing, serving creators, studios, and developers via a hosted platform and research releases. The company operates as a privately held research lab focused on open, state-of-the-art video models. Genmo raised a Series A in 2024. Candidates can expect work on text-to-video, image-to-video, and related multimodal systems used in content production workflows.