Lead Research Scientist: 3D Reconstruction & SLAM

Spaitial Ltd.; Greater London; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

SpAItial in London is seeking a Research Scientist focused on 3D reconstruction to advance pose estimation, geometry recovery, and dense depth from real-world imagery, blending classical geometry with learned methods.

You will design robust SfM/SLAM pipelines, integrate state-of-the-art reconstructors, and collaborate with researchers to push production-ready solutions across robotics, AR/VR, and visual simulation.

Qualifications

• PhD in computer vision with a focus on 3D reconstruction and top-tier publications.
• Strong grasp of multi-view geometry, camera models, epipolar geometry, triangulation, PnP, etc.
• Familiarity with state-of-the-art deep reconstructors and related areas like deep MVS and monocular depth estimation.

Responsibilities

• Design camera pose estimators and 3D reconstructors.
• Build robust SfM and camera tracking pipelines for diverse input sensors.
• Develop bundle adjustment and nonlinear optimization methods.
• Integrate and extend SOTA feed-forward reconstructors (VGGT, DA3, Pi3).
• Advance deep multi-view stereo, learned matching, and monocular depth methods.
• Create evaluation metrics for pose accuracy and reconstruction quality.
• Scale reconstruction methods to large real-world datasets while staying reliable.
• Collaborate with researchers to productionize reconstruction advances.

Skills

Python

PyTorch

Multi-view geometry

3D reconstruction

Education

PhD in computer vision

Tools

COLMAP

ORB-SLAM

Ceres

Job description

SpAItial in London is seeking a Research Scientist focused on 3D reconstruction to advance pose estimation, geometry recovery, and dense depth from real-world imagery, blending classical geometry with learned methods.

You will design robust SfM/SLAM pipelines, integrate state-of-the-art reconstructors, and collaborate with researchers to push production-ready solutions across robotics, AR/VR, and visual simulation.