Real-Time Robot Perception Engineer

Relling; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Relling is seeking a Robot Perception Engineer to develop real-time perception pipelines and integrate cameras, depth sensors, and LiDAR with our robot platforms. You will own segmentation, tracking, and pose estimation, and design observation spaces used by learned controllers on the production line.

This role focuses on robust, end-to-end perception across hardware and software stacks. You will work with the controls and policy teams to ensure outputs feed control loops at the required

Qualifications

• 4+ years of experience in robotics perception, computer vision, or related field.
• Strong software fundamentals in Python and C++.
• Hands-on experience with sensor integration and calibration (cameras, depth sensors, LiDAR, hand‑eye).
• Experience building real‑time perception pipelines on real hardware.
• Fluency with learned and classical CV; ability to choose approach per problem.
• Experience with ROS/ROS2 or similar robotics middleware.
• Ability to debug across the full stack from drivers to model behavior on live hardware.

Responsibilities

• Develop and maintain real-time perception pipelines integrating cameras, depth sensors, and LiDAR with robot platforms.
• Build segmentation, tracking, and pose estimation robust to variation and reflective features.
• Design structured observation spaces and labeling pipelines for training controllers.
• Own the 3D safety perception stack including occupancy prediction and protective stops.
• Connect perception outputs to policy inputs at the control frequency.

Skills

Python

C++

Sensor calibration

ROS/ROS2

Real-time systems

Debugging

Perception pipelines

Tools

TensorRT

PCL

OpenCV

Job description

Relling is seeking a Robot Perception Engineer to develop real-time perception pipelines and integrate cameras, depth sensors, and LiDAR with our robot platforms. You will own segmentation, tracking, and pose estimation, and design observation spaces used by learned controllers on the production line.

This role focuses on robust, end-to-end perception across hardware and software stacks. You will work with the controls and policy teams to ensure outputs feed control loops at the required