SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Niantic Spatial is building geospatial AI powered by a proprietary database of over 30 billion posed images and a third-generation digital map. The mission is to develop spatial intelligence that helps humans and machines understand, navigate, and engage with the physical world.
As Technical Lead for the Applied Computer Vision Algorithms Team, you will drive the "Reconstruct," "Understand," and "Localization" capabilities. The team creates high-fidelity visual and semantic maps—textured semantic meshes and Gaussian Splats—as well as localization maps that enable the Large Geospatial Model (LGM) to perceive the world with human-like precision. You will bridge cutting-edge research and real-world utility, turning complex geospatial data into a persistent sense of space for next-generation AI and robotics.
Key responsibilities include:
- Translating top-tier research papers (CVPR, ECCV, NeurIPS) into production-grade features
- Leading design and implementation of 3D reconstruction pipelines, focusing on Structure from Motion (SfM) and high-fidelity mesh generation, including 3D Gaussian Splats
- Developing and optimizing Gaussian Splatting quality algorithms and ML code for high-performance CPU and GPU execution
- Writing and maintaining high-performance, shader-based production code in C++ for Android and Linux
- Defining technical roadmap and quarterly objectives for the Applied CV Team; mentoring engineers and elevating technical standards
- Partnering with Research and Spatial Solutions teams to translate strategic goals into actionable plans
- Driving quality and benchmarking initiatives to ensure accurate spatial grounding of AI queries with structural, semantic, and location-specific knowledge
REQUIREMENTS:
- 8+ years of professional experience in Computer Vision, Machine Learning, or related field (or 6+ years with a PhD in a relevant domain)
- Bachelor's degree in Computer Science, Engineering, or related technical field; Master's or PhD preferred
- Strong proficiency in C/C++ and Python for production-level software development
- Proven experience in 3D Computer Vision/ML, specifically Structure from Motion (SfM), 3D reconstruction, and Gaussian Splatting rendering techniques
- Demonstrated ability to optimize algorithms for GPUs in Android or Linux environments
- Experience with computer graphics and C++ shader-based implementations
- Previous experience tech leading a team of computer vision engineers in a high-growth environment
- Position requires 3 days per week in San Francisco or Sunnyvale office
