Senior Computer Vision Engineer, Embodied AI

Niantic Spatial builds spatial AI models and services so people and machines can reason, learn and act safely in the physical world. The Senior Computer Vision Engineer will join the Embodied AI team, focused on 3D scene understanding and semantics, working hand in hand with Research Scientists to turn advances in open-vocabulary perception, 3D semantic labeling, and scene graph construction into reliable capabilities for embodied AI teams in production. This is a hands-on applied research role based in the San Francisco office with three days per week in office.

Responsibilities

Productionize 3D scene understanding capabilities by turning research prototypes in open-vocabulary segmentation, 3D semantic and instance labeling, affordance prediction, and scene graph construction into reliable pipeline components and services; Own end-to-end output quality, ensuring reconstructed environments carry consistent, complete, and correct labels, instances, and relationships; Bridge research and production by pressure-testing new methods on real customer data and bringing production and customer constraints back into research planning; Make systems robust to the real world by diagnosing failures caused by capture quality, scene complexity, scale, calibration, coordinate conventions, and other assumptions; Build evaluation and quality infrastructure, including datasets, regression tests, quality gates, and benchmarking tools; Improve performance, throughput, and cost by profiling and optimizing GPU and distributed workloads and reducing unnecessary reruns; Work across the product boundary with Embodied AI product and engineering teams to deliver capabilities that fit real training, evaluation, and deployment workflows

Requirements

5+ years of computer vision experience and a bachelor's degree or equivalent; Significant experience building and operating production computer-vision, machine-learning, graphics, or data-processing systems; Deep hands-on experience with scene understanding: semantic, instance, or panoptic segmentation; open-vocabulary detection and segmentation; or vision-language models applied to perception; Experience taking 2D perception into 3D, such as multi-view label fusion, 3D semantic segmentation, instance tracking across views, or scene graph construction over reconstructed geometry; Experience delivering reliable computer-vision or 3D systems used by other teams or customers, including the evaluation that proved they worked; Practical command of 3D and spatial data, including geometry, camera models, coordinate frames, calibration, and metric scale; Strong Python and PyTorch skills, with the ability to work in C++ or other performance-oriented environments when needed; Experience with cloud infrastructure, GPU workloads, distributed processing, or large-scale data pipelines

Nice to have

Hands-on experience with 3D reconstruction, photogrammetry, structure from motion, Gaussian splatting, neural rendering, or meshing; Experience with SLAM, visual positioning, localization, or large-scale mapping systems; Experience with robotics, simulation, or embodied AI applications, in particular how semantic labels are consumed by a policy or a simulator; Built evaluation or benchmarking infrastructure for perception or reconstruction systems; Experience optimizing large-scale GPU inference workloads for cost, throughput, or latency; A publication record or contributions to widely used open-source perception codebases; Advanced degree in computer vision, robotics, machine learning, or a related field

Benefits

Annual bonus; equity; comprehensive benefits package including medical, dental, and vision coverage; 401(k); and more