Senior 3D Reconstruction & Neural Rendering Scientist

Spaitial Ltd.; Greater London; On-site; GBP 110,000 - 150,000; Full time

Job summary

SpAItial is pursuing state-of-the-art 3D reconstruction through research on Gaussian splats, radiance fields, and modern scene representations. The role involves selecting representations and methods, then improving them across per-scene optimization to feed-forward models, with senior, hands-on expectations.

Applicants should have a PhD in CV/graphics and a track record of reconstruction research across multiple representations, including deep learning frameworks, and a history of publishing in

Qualifications

• PhD in computer vision, graphics, or a related field.
• Publications at top venues (CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS).

Responsibilities

• Advance the state of the art in 3D reconstruction, from research ideas to working methods.
• Work across the full range of reconstruction problems (geometry, appearance, materials, lighting and dynamics, from sparse or incomplete observations).
• Design losses, priors, and optimization strategies to improve fidelity and robustness.
• Build rigorous evaluations on public and internal benchmarks and use them to drive decisions.
• Collaborate with research and engineering colleagues to bring methods into production systems.

Skills

Gaussian splats

Radiance fields

Multi-view geometry

Deep learning

Academic research

Education

PhD in CV/graphics

Tools

Deep learning frameworks

Job description

SpAItial is pursuing state-of-the-art 3D reconstruction through research on Gaussian splats, radiance fields, and modern scene representations. The role involves selecting representations and methods, then improving them across per-scene optimization to feed-forward models, with senior, hands-on expectations.

Applicants should have a PhD in CV/graphics and a track record of reconstruction research across multiple representations, including deep learning frameworks, and a history of publishing in