1 year ago
Responsibilities
- Train foundation diffusion models for image and video generation.
- Train controllability modules such as IP-Adapters and ControlNets.
- Develop novel research techniques and put them into production.
- Conduct large-scale experiments on high-performance computing clusters.
- Optimize data pipelines for massive image datasets.
Requirements
- A proven track record working with image or video models at scale is required.
- Experience with publications or open-source contributions is a plus.
- A strong background in deep learning frameworks and distributed training paradigms is required.
- The ability to iterate rapidly and propose creative research directions is required.
Categories
AI ResearchML Engineering
About Krea
Krea builds a generative-AI creative platform for designers, marketers, and product teams to generate, edit, and enhance images, video, and 3D content. It offers browser-based tools and APIs under subscription plans for individuals and businesses, pairing a research lab’s models with production-grade infrastructure. Privately held and headquartered in San Francisco, the company operates 1000+ Kubernetes GPU clusters and petabyte-scale data pipelines to serve real-time creative workflows.