Staff Autonomy Engineer (MHE Vision)

Are you ready to build the future of supply chain? At Gather AI, we’re not just creating software; we’re pioneering a new era of warehouse intelligence. We’ve developed a groundbreaking, vision-powered platform that uses autonomous drones and existing equipment to capture real-time data, completely digitizing workflows that have historically been manual and error-prone. This means facilities operate smarter, safer, and more efficiently, ultimately redefining “on-time, in full” delivery.

If you’re looking for an opportunity to contribute to truly transformative technology and make a significant impact in a vital industry, Gather AI is the place for you. We’re leading the charge in the rapidly evolving robotics industry, and we invite you to join us in reshaping the global supply chain, one intelligent warehouse at a time.

Our Autonomy team builds the software that makes Gather AI’s MHE Vision and drone products work in live warehouse environments. MHE Vision turns forklifts and other material handling equipment into real-time inventory sensors, using onboard cameras and compute to scan locations and report inventory data as equipment moves through the facility. It’s a technically demanding product line operating at the intersection of embedded systems, computer vision, and large-scale warehouse deployments.

We’re looking for a Staff Autonomy Engineer (MHE Vision) to own the core autonomy software stack for our MHE Vision platform. You’ll lead the design and implementation of the perception, localization, and scanning pipelines that run on vehicle-mounted hardware in production warehouses, and you’ll do it on real systems with real constraints.

This is a Staff-level individual contributor role with significant technical ownership. You’ll work directly with hardware, field deployment, and ML teams to build software that performs reliably in environments that are noisy, dynamic, and unforgiving of edge cases. Your work will directly shape the accuracy and reliability of inventory data that customers depend on.

• →Own the autonomy software stack for Gather products, including perception, localization, and inventory scanning pipelines running on vehicle-mounted embedded compute
• →Contribute to the architecture of the product autonomy stack as the product scales to more vehicle types, facility layouts, and customer configurations
• →Document existing systems
• →Plan future revisions
• →Contribute and lead to design improvements and testing
• →Solve problems across the autonomy stack
• →Design and implement algorithms that reliably detect, identify, and record inventory locations as forklifts and drones move through warehouse aisles under variable lighting, occlusion, and motion
• →Improve scan accuracy and coverage through algorithmic improvements, better sensor integration, and tighter coordination with the ML perception models
• →Build and maintain the software systems that manage scan triggering, location mapping, and data handoff to the cloud platform
• →Collaborate with hardware and field teams to diagnose and resolve issues on deployed systems, using log data and field observations to drive improvements

• 7+ years of software engineering experience with at least 3 years building autonomy, robotics, or perception systems that run on physical hardware in production
• Strong C++ and Python, with experience writing software that runs on embedded or resource-constrained compute platforms
• Hands-on experience with computer vision pipelines including camera-based detection, localization, or tracking in real-world environments
• Experience building and debugging software on deployed systems, including log-based diagnosis and field iteration
• Comfort operating at Staff level: setting technical direction, making consequential architecture decisions, and taking end-to-end ownership of a system

• Experience with ROS2 or similar robotics middleware in a production context
• Background in warehouse, logistics, or industrial automation environments
• Familiarity with sensor fusion, calibration, or multi-camera systems
• Experience with SLAM, odometry, or other localization approaches on mobile platforms