Research Scientist (3D Reconstruction)

Location: On-site in London or Munich

Company

hirify.global develops 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

• Design camera pose estimators and 3D reconstructors for real-world imagery.
• Build robust structure-from-motion and camera-tracking pipelines for different imaging sensors.
• Develop bundle adjustment systems and nonlinear optimizers, including non-perspective camera formulations.
• Integrate and extend state-of-the-art feed-forward reconstructors such as VGGT, DA3, and Pi3.
• Advance deep multi-view stereo, learned matching, and monocular depth methods for dense geometry.
• Build evaluation metrics, scale reconstruction methods to diverse datasets, and transfer research advances into production systems.

Requirements

• PhD in computer vision with a research focus on 3D reconstruction.
• Publications at top venues such as CVPR, ICCV, ECCV, or NeurIPS.
• Deep understanding of camera models, epipolar geometry, triangulation, PnP, and other multi-view geometry concepts.
• Strong familiarity with deep reconstructors, deep multi-view stereo, learned matching, and monocular depth estimation.
• Hands-on experience with SfM/SLAM systems such as COLMAP and ORB-SLAM, and nonlinear least-squares solvers such as Ceres.
• Strong Python and PyTorch skills, with the ability to debug failure cases in challenging real-world data.

Nice to have

• Experience shipping production-grade 3D reconstruction systems.

Culture & Benefits

• Work on generative AI, computer vision, and physically grounded 3D world models.
• Collaborate with researchers to bring reconstruction advances into production.
• Inclusive workplace committed to diversity and equal opportunity.
• Environment focused on creativity, complex problem-solving, dedication, and shared excellence.