Research Scientist - 3D Reconstruction (SfM & SLAM)

SpAItial AI

München

On-site

EUR 90,000 - 130,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

SpAItial in Munich is seeking a Research Scientist focused on 3D reconstruction. You will advance methods to recover camera poses and geometry from real-world imagery, combining classical multi-view geometry with state-of-the-art learned reconstructors.

You will work on SfM, SLAM, depth estimation, and large-scale datasets, collaborating with researchers to deploy advances into production. A PhD in CV and strong Python/PyTorch skills are required.

Qualifications

  • PhD in computer vision with a focus on 3D reconstruction and publications in top venues (CVPR/ICCV/ECCV/NeurIPS).
  • Deep understanding of multi-view geometry: camera models, epipolar geometry, triangulation, PnP, etc.
  • Hands-on experience with SfM/SLAM systems (COLMAP, ORB-SLAM) and nonlinear least-squares solvers (Ceres).
  • Experience shipping production-grade 3D reconstruction systems is a strong plus.
  • Strong Python and PyTorch skills.

Responsibilities

  • Design camera pose estimators and 3D reconstructors.
  • Build robust SfM and camera tracking pipelines for diverse input sensors.
  • Develop bundle adjustment and nonlinear optimizers, including non-perspective camera formulations.
  • Integrate and extend state-of-the-art feed-forward reconstructors (VGGT, DA3, Pi3).
  • Advance deep multi-view stereo, learned matching, and monocular depth methods for dense geometry.
  • Build evaluation metrics for pose accuracy and reconstruction quality, and benchmark improvements.

Skills

Python
PyTorch
COLMAP
ORB-SLAM
Ceres

Education

PhD in Computer Vision

Tools

COLMAP
ORB-SLAM
Ceres Solver

Job description

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments.

We're seeking a Research Scientist focused on 3D reconstruction. You will advance methods that recover accurate camera poses and geometry from real-world imagery, working with both classical multi-view geometry and state-of-the-art learned reconstructors. The work includes structure-from-motion, bundle adjustment, SLAM, or feed-forward reconstruction, with a focus on robustness, accuracy, and methods that hold up on diverse real-world data.

Responsibilities
  • Design camera pose estimators and 3D reconstructors.
  • Build robust SfM and camera tracking pipelines for a variety of input imaging sensors.
  • Develop bundle adjusters and nonlinear optimizers, including non-perspective camera formulations.
  • Integrate and extend SOTA feed-forward reconstructors (VGGT, DA3, Pi3)
  • Advance deep multi-view stereo, learned matching, and monocular depth methods for dense geometry.
  • Build evaluation metrics for pose accuracy and reconstruction quality, and drive improvements against public & internal benchmarks.
  • Scale reconstruction methods to large, diverse real-world datasets while keeping them reliable and efficient.
  • Collaborate with researchers to bring reconstruction advances into production systems.
Key Qualifications
  • PhD in computer vision with a research focus on 3D reconstruction; publications at top venues (CVPR, ICCV, ECCV, NeurIPS).
  • Deep understanding of multi-view geometry: camera models, epipolar geometry, triangulation, PnP, etc.
  • Strong familiarity with SOTA deep reconstructors (VGGT, DA3, Pi3) and related areas such as deep MVS, learned matching, and monocular depth estimation.
  • Hands-on experience with SfM/SLAM systems (COLMAP, ORB-SLAM) and nonlinear least-squares solvers (Ceres).
  • Experience shipping production-grade 3D reconstruction systems is a strong plus.
  • Strong Python and PyTorch skills.
  • Comfortable debugging failure cases on challenging real-world data.

At SpAItial, we are committed to creating a diverse and inclusive workplace. We welcome applications from people of all backgrounds, experiences, and perspectives. We are an equal opportunity employer and ensure all candidates are treated fairly throughout the recruitment process.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Research Scientist - 3D Reconstruction (SfM & SLAM)
Research Scientist - 3D Reconstruction (SfM & SLAM)

SpAItial • München

On-site
EUR 110,000 - 150,000
Research Engineer - 3D Reconstruction
Research Engineer - 3D Reconstruction

SpAItial AI • München

On-site
EUR 90,000 - 135,000
Research Scientist - 3D Reconstruction & Novel View Synthesis
Research Scientist - 3D Reconstruction & Novel View Synthesis

SpAItial AI • München

On-site
EUR 90,000 - 130,000
PhD Research Intern, 3D World Models
PhD Research Intern, 3D World Models

SpAItial AI • München

On-site
EUR 17,000 - 26,000
Research Engineer - 3D World Models
Research Engineer - 3D World Models

SpAItial • München

On-site
EUR 60,000 - 80,000
PhD Research Intern: 3D Vision & SLAM
PhD Research Intern: 3D Vision & SLAM

EngineersOfAI • Germany

Hybrid
USD 22,000 - 36,000
AI Research Intern (PhD) – 3D Computer Vision
AI Research Intern (PhD) – 3D Computer Vision

EngineersOfAI • Germany

Hybrid
USD 22,000 - 36,000
Master Thesis - End-to-End 3D Reconstruction for Non-Pinhole Automotive Cameras (m/f/d)
Master Thesis - End-to-End 3D Reconstruction for Non-Pinhole Automotive Cameras (m/f/d)

Spleenlab • Saalburg-Ebersdorf

On-site
EUR 12,000 - 18,000
Work-Life-Balance: Flexible working
Ergonomic Workstations
Company Events
+1
Research Scientist - 3D Diffusion
Research Scientist - 3D Diffusion

SpAItial • München

On-site
EUR 70,000 - 100,000
Research Scientist - World Models
Research Scientist - World Models

SpAItial • München

On-site
EUR 65,000 - 85,000