Software Engineer - Perception

Voxel•San Francisco, CA

About The Position

Industrial labor is incredibly dangerous work—nearly 3 million people in the US are injured in the workplace each year due to entirely preventable and sometimes fatal or debilitating causes. Protecting these essential workers who power our world is what motivates Voxelitos, and we would love for you to join us. At Voxel, we are passionate about revolutionizing workplace safety and operations with groundbreaking, full-stack AI and computer vision technology. Voxel’s site intelligence platform helps safety and operations leaders identify unseen risks, make strategic decisions, and prevent workplace incidents before they occur. Our customers include Fortune 500 companies across major grocers and retailers, manufacturers, food and beverage warehouses, and supply chain and logistics service providers. Based in SF with team members located all over the globe, Voxel is backed by industry-leading VCs. We are seeking a highly motivated and bright engineer to join our team and devise elegant solutions to challenging problems. This role will focus on designing and implementing systems to support Voxel's ML development. As a part of the perception team, you should be comfortable working in a fast-paced environment and solving problems across the software stack. We require engineers to be versatile and possess the ability to move across projects and tackle new challenges.

Requirements

Bachelor's degree in Computer Science, Robotics or a related field.
Software development experience with proficiency in Python, Go-Lang or C++.
Ability to solve complex and open-ended problems
Familiarity with version control systems like Git (e.g., branching, merging, pull requests).

Nice To Haves

Master’s or PhD in Computer Science, Robotics, or a related field.
Coursework or research in computer vision or machine learning.
1-3 years of experience in software development.
Experience with Docker, Bazel build system and/or AWS cloud services like EKS, S3, ECS
Experience designing large, highly available distributed systems with Kubernetes.
Experience working with monocular cameras - pose estimation, tracking and state estimation, object detection, segmentation.

Responsibilities

Develop and productionize state-of-the-art computer vision algorithms for object detection, tracking, pose estimation, activity recognition, and anomaly detection in complex indoor environments like warehouses and retail spaces.
Implement and optimize computer vision techniques for high-throughput, low-latency applications on edge compute devices.
Streamline ML data ingestion, retraining pipelines, and model redeployment workflows.
Build and maintain reliable, scalable pipelines for continuous training and deployment of ML models in production environments.
Partner with Sales, Customer Success, and Field Engineering to architect ML-driven solutions tailored to customer needs and deployment contexts.