spaitial - Research Scientist
Upload My Resume
Drop here or click to browse · Tap to choose · PDF, DOCX, DOC, RTF, TXT
Requirements
• PhD in Computer Science or related field with a top-tier publication record in ML, Vision or graphics from reputable conferences such as CVPR, ECCV/ICCV, NeurIPS, SIGGRAPH. • Strong knowledge of generative models like image or video diffusion and cutting-edge architectures including diffusion transformers (DiT). • Rich experience with deep learning frameworks particularly PyTorch. • Expert coding skills along with the ability to rapidly iterate through ML experiments using modern AI tools.
Responsibilities
• Architect generative world models that reason about space, time, and physics. • Design and develop image/video diffusion foundational ML models. • Large-scale distributed model training on top of distributed cloud infrastructure. • Develop demos showcasing the trained model prototypes. • Processing and maintaining large data for model training. • Productionizing models, test-time model optimization.
Benefits
• None stated in this job posting.
No credit card. Takes 10 seconds.