We are looking for a Computer Vision Research Engineer to join our Research Team in London. Our team researches and builds the 3D reconstruction technology behind Niantic Spatial’s platform, transforming casually captured or domain‑specific imagery into high‑fidelity, explorable 3D reconstructions. You will work at both ends of the pipeline – from academic publishing to production – collaborating with world‑class researchers in computer vision, machine learning, graphics, and robotics.
Location & Work Arrangement
London, UK – Hybrid model with a minimum of three days per week in the office. Niantic Spatial sponsors work visas for many roles; we cannot guarantee sponsorship for every candidate but will make a reasonable effort to support work authorization if we make you an offer.
Responsibilities
- Conduct original research in computer vision, machine learning, and spatial AI.
- Design, implement, and evaluate novel algorithms for 3D reconstruction, neural scene representations, 3D Gaussian splatting, geometric deep learning, Structure‑from‑Motion (SfM), feed‑forward models, and spatial foundation models.
- Collaborate with research scientists and engineers to transition promising ideas into future products.
- Develop large‑scale experiments and benchmarking frameworks.
- Work directly with production realities: real capture conditions, hardware constraints, and real customers.
- Publish research findings at leading conferences such as CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, etc.
Qualifications
- PhD in Computer Vision, Robotics, Machine Learning, Computer Science, Mathematics, Physics, or a closely related field. Exceptionally strong candidates with equivalent industry experience will be considered.
- A strong research track record in 3D computer vision: reconstruction, depth estimation, novel view synthesis, SfM, SLAM, or closely related areas.
- Strong publication record at top‑tier conferences.
- Strong programming skills in Python and experience with PyTorch.
- Evidence of translating research ideas into production‑ready features, pipelines, widely used open‑source releases, or similar tangible outcomes.
- Ability to independently drive research projects from idea generation through experimentation and publication.
Nice to Have
- Experience with classical reconstruction tooling such as COLMAP.
- Knowledge of C++ or CUDA and an understanding of performance optimization and on‑device constraints.
