Research Engineer 3D Reconstruction
SpAItialVisit SpAItial website
SpAItial is a London AI company developing physically grounded world models that generate and reason about explorable 3D environments.
London, United Kingdom
Funding history
About SpAItial
SpAItial develops the Echo model family and an app/API for generating, editing, exploring, sharing, and exporting persistent 3D Gaussian Splat worlds from text, images, and panoramas.
Skills
About the Role
You will advance 3D reconstruction methods from research ideas to working implementations. You will address geometry, appearance, materials, lighting, incomplete observations, dynamic scenes, and large-scale environments. You will evaluate methods rigorously, tune optimization approaches, and help move successful methods into production systems.
Requirements
- Bachelor’s or Master’s degree, or equivalent experience, in computer science, computer vision, graphics, or a related field
- Hands-on knowledge of modern scene representations, including Gaussian splats and radiance fields
- Experience with reconstruction methods from per-scene optimization to feed-forward models
- Understanding of multi-view geometry, camera models, and rendering
- Experience with deep learning frameworks
- Strong coding skills and ability to implement methods from papers
Responsibilities
- Advance 3D reconstruction methods from research ideas to working methods
- Address reconstruction problems involving geometry, appearance, materials, lighting, incomplete observations, dynamic scenes, and large-scale environments
- Build and improve methods from per-scene optimization to feed-forward models
- Implement, adopt, or extend scene representations
- Tune losses, priors, and optimization strategies
- Build rigorous evaluations using public and internal benchmarks
- Bring successful methods into production systems