SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
SpAItial is building next-generation World Models that push the boundaries of generative AI, computer vision, and physics-aware 3D simulation. The company is moving beyond 2D pixels to create models that natively understand the geometry and physics of the real world, with applications across robotics, AR/VR, gaming, and cinema.
As a Research Scientist in 3D Reconstruction & Novel View Synthesis, you will advance the state of the art in 3D reconstruction from research conception through working implementations. You will work across the full spectrum of reconstruction challenges—geometry, appearance, materials, lighting, and dynamics—from sparse or incomplete observations. Your work will span novel view synthesis, neural rendering, and feed-forward view generators.
Key responsibilities include:
- Advancing state-of-the-art 3D reconstruction methods, from ideation to deployment
- Tackling diverse reconstruction problems across geometry, appearance, materials, lighting, and dynamics
- Designing losses, priors, and optimization strategies to improve fidelity, robustness, and efficiency
- Building rigorous evaluations on public and internal benchmarks to drive technical decisions
- Collaborating with research and engineering teams to transition successful methods into production systems
This is a senior, hands-on research role requiring deep expertise in modern scene representations and the ability to select and improve upon the right approach for each problem.
Requirements:
- PhD in computer vision, graphics, or related field with publications at top-tier venues (CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS)
- Deep, hands-on knowledge of modern scene representations (e.g., Gaussian splats, radiance fields) and ability to evaluate their trade-offs
- Research experience across the reconstruction spectrum, from per-scene optimization to feed-forward models
- Deep understanding of multi-view geometry, camera models, and rendering
- Strong experience with deep learning frameworks
