We're looking for a Robot Perception Engineer to develop and maintain the perception systems that give our humanoid robots a real-time understanding of the world around them. You'll own the software that transforms raw sensor data into reliable, actionable perception - from sensor integration and calibration to safety-certified object detection and streaming data to our foundation models and teleoperation stack.
What You'll Do- Develop and maintain real-time perception pipelines - integrating and calibrating sensors (cameras, LiDAR, IMUs, depth sensors) with our humanoid robot platforms
- Build and optimize object detection, tracking, and scene understanding systems for safe operation in complex, unstructured environments
- Own the streaming infrastructure that delivers sensor data reliably to foundation models, teleoperation systems, and onboard control stacks
- Work closely with the AI/ML team to bridge perception outputs and learned policy inputs - ensuring low-latency, high-reliability data delivery
- Implement and validate safety-certified perception components, including object detection and collision avoidance, to meet real-world deployment requirements
- Support bring-up and field testing of new camera hardware and sensor configurations
- Contribute to system reliability, fault detection, and recovery logic for robust real-world perception
What We're Looking For- 4+ years of experience in robotics perception, computer vision, or a closely related field
- Strong software engineering fundamentals in C++, Python, or Rust
- Hands-on experience with sensor integration and calibration (cameras, LiDAR, IMUs, depth sensors)
- Experience building real-time perception pipelines on embedded or edge compute platforms
- Familiarity with streaming and networking systems for low-latency sensor data transport
- Experience with ROS/ROS2 or similar robotics middleware in production or research contexts
- Ability to debug across the full stack - from driver-level sensor issues to perception behavior on live hardware
Nice to Have (But Not Required)- Experience with safety-certified or safety-critical perception systems (e.g., ISO 26262, IEC 61508, or similar)
- Background in multi-sensor fusion and calibration for robust perception under real-world conditions
- Familiarity with teleoperation systems and the latency and reliability constraints they impose
- Experience deploying and optimizing perception models on edge or onboard compute (quantization, TensorRT, etc.)
- Familiarity with humanoid or legged robot platforms and the unique perception challenges they present
- Prior work on early-stage hardware programs (prototype or pre-production robots)
Why This Role- Your perception stack is the robot's eyes - the software you write directly determines what our humanoids can see, understand, and safely interact with in the real world
- Work at the boundary of hardware and AI, integrating state-of-the-art sensors and learned perception models onto real robotic systems
- High ownership in a small, fast-moving team where your contributions shape how the next generation of humanoid robots perceive and navigate the world
