Niantic Spatial builds real-world foundational models for physical AI, so people and machines can work efficiently and safely together. Backed by Javelin Venture Partners.
About the role
Applied Research & Implementation: Actively translate top-tier research papers (e.g., from CVPR, ECCV, NeurIPS) into production-grade features within our tech stack. Technical Leadership: Lead the design and implementation of 3D reconstruction pipelines, focusing on Structure from Motion (SfM) and high-fidelity mesh generation as well as 3D gaussian splats.
What they're looking for
- Years of Experience: 8+ years of professional experience in Computer Vision, Machine Learning, or a related field (or 6+ years with a PhD in a relevant domain)
- Education: Bachelor’s degree in Computer Science, Engineering, or a related technical field, Master's or PhD preferred
- Core Technical Skills: Strong proficiency in C/C++ and Python for production-level software development
- Specialized Expertise: Proven experience in 3D Computer Vision/ML, specifically with Structure from Motion (SfM), 3D reconstruction, and Gaussian Splatting rendering techniques
- Hardware Optimization: Demonstrated ability to optimize algorithms for GPUs in Android or Linux environments
- Graphics Knowledge: Experience with computer graphics and C++ shader-based implementations
More about this role
At Niantic Spatial, we’re building the future of geospatial AI. Powered by a proprietary database of over 30 billion posed images and a groundbreaking third-generation digital map, our mission is to develop spatial intelligence that helps both humans and machines better understand, navigate, and engage with the physical world. Our high-fidelity mapping technology unlocks a new dimension of interaction—laying the foundation for AI to truly comprehend and operate within real-world environments. Join us as we build a living model of the world that people and machines can talk to.
As a Tech Lead for the Applied Computer Vision Algorithms Team, you’ll help drive our “Reconstruct”, “Understand” and “Localization” capabilities. This team is responsible for creating the high-fidelity visual and semantic maps—specifically textured, semantic meshes, and Gaussian Splats— as well as localization maps that allow our Large Geospatial Model (LGM) to perceive the world with human-like precision. Closely working with the R&D and product teams your work will bridge the gap between cutting-edge theory and real-world utility, turning complex geospatial data into a persistent sense of space for the...
Browse similar: AI jobs · AI startup jobs · Startup jobs · Remote jobs · San Francisco Bay Area