
Staff/Senior Staff Computer Vision Engineer - Map team
Niantic Spatial25 days ago
Base Salary
$257k - $315k/yr
Responsibilities
- Lead the design and implementation of Structure from Motion, feed-forward and foundational models, 3D reconstruction, meshing, and Gaussian Splatting technologies.
- Research and develop novel solutions for Visual Positioning Systems and 3D reconstruction.
- Design, develop, and maintain scalable production-grade computer vision systems for VPS, reconstruction, and mapping pipelines.
- Develop, train, and optimize algorithms for accurate and high-performance CPU/GPU execution on cloud or device.
- Create high-quality data and benchmarking systems for spatial grounding and AI-readable world models.
- Define technical roadmaps and quarterly objectives while providing technical leadership, mentorship, and code governance.
- Collaborate with Product, Research, and Operations teams to deliver computer vision solutions.
Requirements
- 7+ years of professional experience in computer vision, machine learning, or a related field, or 4+ years with a relevant PhD.
- Bachelor’s degree in Computer Science, Engineering, or a related technical field; a Master’s or PhD is preferred.
- Strong proficiency in Python and/or C/C++.
- Proven experience with classical and learned-based 3D computer vision and machine learning.
- Experience taking research into production at scale.
- Previous experience technically leading computer vision projects.
Benefits
- Annual bonus, equity, medical, dental, vision, 401(k), and additional comprehensive benefits.
- Role is based in the San Francisco or Sunnyvale office and requires three days per week in office.
Categories
About Niantic Spatial
Niantic Spatial builds computer‑vision and spatial computing software that maps real‑world environments and localizes people and machines within them. The company offers a platform with APIs and SDKs for creating AI‑native digital twins, visual positioning, and spatial question‑answering, serving robotics, AR/VR, defense, and industrial operations. Privately held, it sells its technology to enterprises that need precise, geometrically accurate understanding of physical spaces beyond GPS or screen‑bound systems.