Research Engineer 3D World Models
SpAItialVisit SpAItial website
SpAItial is an AI company building physically grounded world models that generate persistent, explorable 3D worlds from text, images, and panoramas.
London, United Kingdom
Funding history
About SpAItial
SpAItial Ltd operates the Echo model family, a spatial-AI product available through a web app and developer API for generating, editing, sharing, and exporting 3D Gaussian Splat worlds.
Skills
About the Role
You will develop generative methods for physically grounded 3D environments. You will build, train, optimize, and evaluate models for reconstruction, view synthesis, and world generation; experiment with 3D representations; develop training pipelines and loss functions; and improve model quality and robustness.
Requirements
- Strong fundamentals in deep learning and generative models
- Understanding of diffusion models and transformers
- Understanding of camera geometry, depth, reconstruction, point clouds, meshes, or Gaussian splats
- Proficiency in Python and PyTorch
- Experience with model training and optimization
- Ability to implement research papers and run experiments
- Strong coding skills for scalable ML systems
Responsibilities
- Design and develop generative 3D machine-learning methods
- Build, train, optimize, and evaluate models for 3D reconstruction, novel-view synthesis, and world generation
- Implement 3D representations including point clouds, meshes, and Gaussian splatting
- Develop training pipelines and loss functions
- Integrate physics-aware priors and world-model capabilities
- Analyze model performance, debug failures, and improve quality and robustness