Senior Software Engineer – 3D Vision and SLAM

Claryo•San Francisco, CA

2d•Hybrid

About The Position

We're looking for a Computer Vision / SLAM Engineer to drive the development of our Spatial Generative AI platform that revolutionizes how warehouses operate through advanced 3D perception and autonomous systems. You'll own the design and implementation of cutting-edge computer vision algorithms that enable cameras, drones and handheld devices to create precise 3D representation of warehouse environments, track inventory in real-time, and power our robotic simulation platform. If you're passionate about pushing the boundaries of 3D reconstruction, neural scene representation, and real-time object tracking at scale, we'd love to hear from you. This is a deeply technical role at the intersection of SLAM, neural rendering, and multi-camera tracking systems. You'll work closely with our perception, infrastructure, and product teams to deliver production-ready vision systems that scale across diverse warehouse environments. You’ll contribute to our visual perception backbone that enables truly autonomous warehouse operations. We've found tremendous value in collaborative problem-solving, so our team works from our SF office three days a week.

Requirements

PhD or MS in Computer Science, Robotics, Electrical Engineering, or related field with 3+ years of industry experience, or BS with 6+ years building production vision systems.
Deep expertise in SLAM or Structure from Motion, including bundle adjustment, factor graph optimization, and multi-view geometry.
Hands-on experience with neural scene representations (3D Gaussian Splatting) and camera calibration pipelines.
Track record of shipping computer vision products in production environments.
Strong programming skills in Python or C++.

Nice To Haves

Experience with deep neural networks for computer vision (CNNs, Vision Transformers) and semantic segmentation.
Background in multi-object detection and tracking across multiple camera views.
Experience with ROS, point cloud processing, game engines (Unreal, Unity), or CUDA programming.
Publications in top-tier computer vision or robotics conferences (CVPR, ICCV, ECCV, ICRA, etc.).

Responsibilities

Design and implement 3D mapping and reconstruction algorithms using SLAM, Structure from Motion, and neural scene representations (Gaussian Splatting).
Architect multi-camera mapping, localization, and real-time 3D object detection and tracking systems.
Build data acquisition and camera calibration pipelines for 2D/3D mapping using drones and handheld devices.
Build sensor simulation pipelines for warehouse and robotics simulation.
Optimize computer vision pipelines for cloud GPU deployment and establish evaluation frameworks for production environments.