Research Scientist (3D Reconstruction)

Location: On-site in London or Munich

Company

Building generative AI and computer vision models that understand the physics and geometry of the real world to generate physically grounded 3D environments.

What you will do

• Advance 3D reconstruction research from initial ideas to working methods.
• Develop solutions for geometry, appearance, materials, lighting, dynamics, sparse observations, and novel view synthesis.
• Work with neural rendering and feed-forward view generation methods.
• Design losses, priors, and optimization strategies to improve fidelity, robustness, and efficiency.
• Build evaluations on public and internal benchmarks and use results to guide research decisions.
• Collaborate with research and engineering colleagues to integrate successful methods into production systems.

Requirements

• PhD in computer vision, graphics, or a related field.
• Publications at leading venues such as CVPR, ICCV, ECCV, SIGGRAPH, or NeurIPS.
• Deep, hands-on knowledge of modern scene representations, including Gaussian splats and radiance fields.
• Research experience across multiple reconstruction approaches, from per-scene optimization to feed-forward models.
• Strong understanding of multi-view geometry, camera models, and rendering.
• Strong experience with deep learning frameworks.

Culture & Benefits

• Inclusive workplace welcoming people from diverse backgrounds, experiences, and perspectives.
• Equal opportunity employment and fair treatment throughout the recruitment process.