Dein persönlicher KI-Karriere-Agent
Research Scientist - 3D Diffusion(m/w/x)
Pioneering 3D diffusion models for generative AI and computer vision. PhD in CS, CV, graphics, ML, or related field required. Work on world models with physics and geometry understanding.
Anforderungen
- PhD in computer science, computer vision, graphics, machine learning, or related field
- Top-tier publication record at CVPR, ECCV/ICCV, NeurIPS, and SIGGRAPH
- Strong deep learning and generative modeling fundamentals
- Expertise in diffusion models and large transformer models
- Hands-on training diffusion models experience
- Experience with image and video model stacks
- Solid understanding of 3D processing concepts
- Proficiency in Python
- Proficiency in deep learning frameworks like PyTorch
- Experience in large-scale model training and optimization
- Ability to implement research ideas
- Ability to run rigorous experiments
- Ability to ship reliable ML code
Aufgaben
- Lead research on 3D diffusion models
- Design diffusion-based methods for 3D generation
- Build 3D diffusion models
- Train 3D diffusion models
- Optimize 3D diffusion models
- Evaluate 3D diffusion models
- Research diffusion model architectures
- Research diffusion model losses
- Research diffusion model sampling strategies
- Adapt image diffusion backbones to 3D
- Adapt video diffusion backbones to 3D
- Implement 3D point cloud representations
- Implement 3D mesh representations
- Implement 3D Gaussian Splatting
- Develop training pipelines
- Develop loss functions for geometry accuracy
- Develop loss functions for visual fidelity
- Develop loss functions for spatiotemporal consistency
- Integrate physics-aware priors into diffusion systems
- Integrate world model capabilities into diffusion systems
- Analyze model performance
- Debug model failure cases
- Iterate to improve model quality
- Iterate to improve model robustness
Ausbildung
- Doktor / Ph.D.
Sprachen
- Englisch – verhandlungssicher
Tools & Technologien
- Python
- PyTorch
- Stable Diffusion
- FLUX
- WAN
Gefällt dir diese Stelle?
BetaDein Career Agent findet täglich ähnliche Jobs für dich.
Noch nicht perfekt?
- SpAItialVollzeitnur vor OrtKeine AngabeMünchen
- SpAItial
Research Engineer(m/w/x)
Vollzeitnur vor OrtBerufserfahrenMünchen - NVIDIA
Research Scientist, 3D Computer Vision(m/w/x)
Vollzeitnur vor OrtKeine AngabeMünchen - SpAItial
Research Engineer - Graphics(m/w/x)
Vollzeitnur vor OrtBerufserfahrenMünchen - SpAItial
Machine Learning & Cloud Infra Engineer(m/w/x)
Vollzeitnur vor OrtBerufserfahrenMünchen
Research Scientist - 3D Diffusion(m/w/x)
Pioneering 3D diffusion models for generative AI and computer vision. PhD in CS, CV, graphics, ML, or related field required. Work on world models with physics and geometry understanding.
Anforderungen
- PhD in computer science, computer vision, graphics, machine learning, or related field
- Top-tier publication record at CVPR, ECCV/ICCV, NeurIPS, and SIGGRAPH
- Strong deep learning and generative modeling fundamentals
- Expertise in diffusion models and large transformer models
- Hands-on training diffusion models experience
- Experience with image and video model stacks
- Solid understanding of 3D processing concepts
- Proficiency in Python
- Proficiency in deep learning frameworks like PyTorch
- Experience in large-scale model training and optimization
- Ability to implement research ideas
- Ability to run rigorous experiments
- Ability to ship reliable ML code
Aufgaben
- Lead research on 3D diffusion models
- Design diffusion-based methods for 3D generation
- Build 3D diffusion models
- Train 3D diffusion models
- Optimize 3D diffusion models
- Evaluate 3D diffusion models
- Research diffusion model architectures
- Research diffusion model losses
- Research diffusion model sampling strategies
- Adapt image diffusion backbones to 3D
- Adapt video diffusion backbones to 3D
- Implement 3D point cloud representations
- Implement 3D mesh representations
- Implement 3D Gaussian Splatting
- Develop training pipelines
- Develop loss functions for geometry accuracy
- Develop loss functions for visual fidelity
- Develop loss functions for spatiotemporal consistency
- Integrate physics-aware priors into diffusion systems
- Integrate world model capabilities into diffusion systems
- Analyze model performance
- Debug model failure cases
- Iterate to improve model quality
- Iterate to improve model robustness
Ausbildung
- Doktor / Ph.D.
Sprachen
- Englisch – verhandlungssicher
Tools & Technologien
- Python
- PyTorch
- Stable Diffusion
- FLUX
- WAN
Gefällt dir diese Stelle?
BetaDein Career Agent findet täglich ähnliche Jobs für dich.
Über das Unternehmen
SpAItial
Branche
Research
Beschreibung
The company is pioneering the development of a frontier 3D foundation model, pushing the boundaries of AI, computer vision, and spatial computing.
Noch nicht perfekt?
- SpAItial
Research Scientist - World Models(m/w/x)
Vollzeitnur vor OrtKeine AngabeMünchen - SpAItial
Research Engineer(m/w/x)
Vollzeitnur vor OrtBerufserfahrenMünchen - NVIDIA
Research Scientist, 3D Computer Vision(m/w/x)
Vollzeitnur vor OrtKeine AngabeMünchen - SpAItial
Research Engineer - Graphics(m/w/x)
Vollzeitnur vor OrtBerufserfahrenMünchen - SpAItial
Machine Learning & Cloud Infra Engineer(m/w/x)
Vollzeitnur vor OrtBerufserfahrenMünchen