The Role
As a member of technical staff, you will drive the integration of 3D spatial awareness into our generative models. You are a hands-on researcher and engineer who understands how to lift 2D video models into fully multi-dimensional, physically accurate simulations. You will bridge the gap between traditional 3D vision pipelines and modern foundation models at an industrial scale.
Job Responsibilities
- Design and implement robust 3D pipelines to lift and ground generative video models in accurate spatial dimensions.
- Integrate neural rendering, 3D representations, and temporal dynamics into core model architectures.
Minimum Qualifications
- Extensive practical experience in Computer Science, Machine Learning, 3D Computer Vision.
- Deep technical understanding of 3D pipelines, spatial computing, and geometric deep learning as applied to generative models.
- Direct, hands-on experience training large-scale generative models in a high-compute environment.
- Expert-level software development experience with deep learning frameworks (e.g., PyTorch, JAX).
Preferred Qualifications
- PhD in Computer Science, Computer Vision, or Artificial Intelligence.
- Proven track record of shipping 3D-aware video models or neural rendering systems to production at a top-tier industrial lab.