Senior Computer Vision Engineer, Embodied AI

The role

You will productionize 3D scene understanding capabilities by turning research prototypes into reliable pipeline components. You will work with Research Scientists to adapt methods for real-world data and improve performance, throughput, and cost.

What you will do

• Turn research prototypes in open-vocabulary segmentation, 3D semantic and instance labeling, affordance prediction, and scene graph construction into reliable pipeline components and services.
• Ensure reconstructed environments carry consistent, complete, and correct labels, instances, and relationships.
• Pressure-test new methods on real customer data and bring production constraints back to research planning.
• Diagnose failures caused by capture quality, scene complexity, scale, calibration, and coordinate conventions.
• Create datasets, regression tests, quality gates, and benchmarking tools.
• Profile and optimize GPU and distributed workloads to improve performance, throughput, and cost.
• Partner with Embodied AI product and engineering teams to deliver capabilities for training, evaluation, and deployment workflows.

Required qualifications

• 5+ years of computer vision experience
• 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
• Practical command of 3D and spatial data, including geometry, camera models, coordinate frames, calibration, and metric scale
• Strong Python and PyTorch skills
• 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
• 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

• Medical coverage
• Dental coverage
• Vision coverage
• 401(k)
• 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.