Senior Software Engineer, Perception Skills
Automate your job search with Sonara.
Submit 10x as many applications with less effort than one manual application.1
Reclaim your time by letting our AI handle the grunt work of job searching.
We continuously scan millions of openings to find your top matches.
Overview
Job Description
About the Role
We are looking for a Senior Software Engineer to join our Skills team, with a focus on integrating perception models into real-world robotic applications. In this role, you will be responsible for perception integration efforts to build robust, structured world representations that can be manipulated and reasoned about in robot workflows. You will own the performance of the perception stack on the robot, working hands-on with real hardware and validating your work in production workflows. You'll collaborate closely with AIML teams and integrate both in-house and off-the-shelf methods to meet customer and task-specific requirements. This role is ideal for someone who wants to be close to the real system, enjoys solving end-to-end integration challenges, and thrives on making perception work reliably in production.
About the Work
- Develop robust perception algorithms and applications that leverage existing perception models and structure in the robot task (e.g., stacks, pallets, conveyors, flowracks) to improve robustness and simplify estimation
- Define and maintain reusable APIs that allow the task planner and skills layer to interact with a library of perception skills
- Integrate perception functions with other robot skills like manipulation behaviors using state machines, behavior trees, and task planners
- Manage datasets and run experiments to validate perception skills across diverse task conditions and variations
- Create modular interfaces for field engineers to tune perception skills within your validated specs without requiring software redeployment
- Contribute to defining our overall perception strategy within the skills layer, including library structure, abstraction layers, and tooling
About You
- BS or MS in Robotics or related field
- 5+ years of professional experience integrating perception models in real-world robotic applications
- Strong experience writing production-quality Python code
- Hands-on experience working with point clouds, RGBD cameras, and depth sensing in applied robotics contexts.
- Experience with perception libraries (OpenCV, Open3D, PCL, ROS perception, NumPy, scikit-image)
- You're pragmatic: you know when to use task structure and prior knowledge to get the job done reliably
- You love solving hard perception problems, but your real passion is seeing those solutions work on a robot in the real world and having an impact
- You're excited to work on hardware
- You enjoy debugging, testing, and iterating quickly in simulation and on the real robot
You Might Also Have
- Solid understanding of spatial reasoning (homogeneous transforms, TF trees, etc)
- Demonstrated ability to apply perception model outputs (detection, segmentation, pose estimation) in manipulation pipelines
- Experience with structured 3D estimation (plane fitting, normal estimation, voxel maps, etc)
Automate your job search with Sonara.
Submit 10x as many applications with less effort than one manual application.