3D Reconstruction Research Scientist

The role

You will conduct original research in computer vision, machine learning, and spatial AI. You will design, implement, and evaluate novel algorithms for 3D reconstruction and neural scene representations to transition ideas into products.

What you will do

• 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, SfM, meshing, feed-forward models, generative mode
• Collaborate with research scientists and engineers to transition promising ideas into future products.
• Develop large-scale experiments and benchmarking frameworks.
• Work with the realities of production with real capture conditions, real hardware constraints, and real customers.
• Publish research findings at leading conferences such as CVPR, ICCV, ECCV, or SIGGRAPH.

Required qualifications

• PhD in Computer Vision, Robotics, Machine Learning, Computer Science, Mathematics, Physics, or a closely related field or equivalent experience in industry.
• 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 such as CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, etc.
• Strong programming skills in Python and experience in PyTorch.
• Evidence that you can carry an idea from research into something real.
• Ability to independently drive research projects from idea generation through experimentation and publication.

Nice to have

• Experience with classical reconstruction tooling (COLMAP or similar).
• C++ or CUDA experience, and a feel for performance and on-device constraints.
• Experience with traditional 3D techniques — meshing, texturing, or bringing modern geometry or generative representations into native 3D.

Benefits

• Annual bonus
• Equity
• Comprehensive benefits package

About the company

Niantic Spatial builds spatial AI models and services so people and machines can reason, learn and act safely in the physical world. They turn camera imagery, video, sensor data and archives into accurate, AI-readable representations of real places.