{"id":799262,"url":"https://alion.io/job/spaitial-research-scientist-3d-reconstruction-sfm-slam","title":"Research Scientist - 3D Reconstruction (SfM & SLAM)","company":{"id":688399,"name":"SpAItial","domain":"spaitial.ai","url":"https://alion.io/company/spaitial","size_band":"201-500","is_staffing_agency":false,"is_intermediary":false,"ats_vendor":"Ashby","truth_index":{"grade":"C","score":64,"open_postings":10,"ghost_share":0.6,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-09-23T05:45:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"hiring_geo_confidence":"structured","locations":["London, United Kingdom","Munich, Germany"],"countries":["GB","DE"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":102000,"max_usd":265000,"period":"year","method":"role_country_seniority_unknown","sample_n":101},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"COLMAP","optional":false},{"name":"Computer Vision","optional":false},{"name":"ORB-SLAM3","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"World Models","optional":false}],"status":"live","first_seen_at":"2026-08-20T11:36:00Z","employer_posted_date":"2026-08-20","last_verified_at":"2026-09-23T12:41:38Z","board_verified":true,"closed_at":null,"days_open":34,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":33},"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.\nWe'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.\nResponsibilities\nDesign camera pose estimators and 3D reconstructors.\n\nBuild robust SfM and camera tracking pipelines for a variety of input imaging sensors.\n\nDevelop bundle adjusters and nonlinear optimizers, including non-perspective camera formulations.\n\nIntegrate and extend SOTA feed-forward reconstructors (VGGT, DA3, Pi3)\n\nAdvance deep multi-view stereo, learned matching, and monocular depth methods for dense geometry.\n\nBuild evaluation metrics for pose accuracy and reconstruction quality, and drive improvements against public & internal benchmarks.\n\nScale reconstruction methods to large, diverse real-world datasets while keeping them reliable and efficient.\n\nCollaborate with researchers to bring reconstruction advances into production systems.\n\nKey Qualifications\nPhD in computer vision with a research focus on 3D reconstruction; publications at top venues (CVPR, ICCV, ECCV, NeurIPS).\n\nDeep understanding of multi-view geometry: camera models, epipolar geometry, triangulation, PnP, etc.\n\nStrong familiarity with SOTA deep reconstructors (VGGT, DA3, Pi3) and related areas such as deep MVS, learned matching, and monocular depth estimation.\n\nHands-on experience with SfM/SLAM systems (COLMAP, ORB-SLAM) and nonlinear least-squares solvers (Ceres).\n\nExperience shipping production-grade 3D reconstruction systems is a strong plus.\n\nStrong Python and PyTorch skills.\n\nComfortable debugging failure cases on challenging real-world data.\n\nAt 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.","description_format":"text","description_chars":2592,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"phd","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Robotic Software & Control Systems","Artificial Intelligence","LLM & Generative AI","Foundation Models"],"lifecycle":[{"event":"open","at":"2026-09-12T06:56:27Z"}],"liveness":{"score":22,"band":"cold","label":"Long shot","p_open":1,"p_active":0.397,"p_room":0.55,"age_days":33,"expected_fill_days":32,"reasons":["conf:1","stale_co","win:tail"],"computed_at":"2026-09-23T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/spaitial-research-scientist-3d-reconstruction-sfm-slam","json_url":"https://alion.io/job/spaitial-research-scientist-3d-reconstruction-sfm-slam.json","meta":{"generated_at":"2026-09-23T18:09:42Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers"}}