At Mentee Robotics, we are redefining humanoid automation with an AI-first approach - combining perception, reasoning, and dexterous manipulation into fully autonomous systems that continuously learn and improve. We offer an exceptional opportunity to participate in building next-generation commercial humanoid robots from 0 to 1, alongside competitive compensation, and an international engineering environment. We are expanding with a new robotics Engineering Center in China, working hand-in-hand with our engineering teams in headquarters. Its mission: to rapidly develop our next-generation full-size humanoid platform and bring it to production.
We are looking for a Sensor Software Engineer to own the architecture, driver development, high-throughput ingestion pipelines, clock synchronization, and data abstraction layers for all perception and proprioceptive sensors (RGB-D cameras, ToF, LiDAR, high-frequency IMU, 6-axis F/T sensors, and tactile arrays) across our humanoid robot.
Who you are:
- Systems developer passionate about low-latency sensor drivers, hardware abstraction layers, cross-sensor clock synchronization, and zero-drop data pipelines.
- Hands-on software craftsman adept at Linux device drivers, SocketCAN, V4L2, GStreamer, zero-copy shared memory, and C++ system design.
- Driven by high data fidelity, deterministic timing, failure resilience, and continuous API clean-up.
- A strong collaborator across perception, state estimation, hardware design, and calibration teams.
Responsibilities:
- Design and maintain robust C++ driver abstraction layers for heterogeneous sensor suites (RGB-D cameras, ToF, LiDAR, high-rate IMUs, tactile sensors, 6-axis force-torque sensors).
- Implement hardware-assisted time synchronization protocols (IEEE 1588 PTP, gPTP, PPS, hardware sync trigger lines) across distributed sensor nodes and central compute.
- Develop low-latency zero-copy data transport pipelines to deliver high-bandwidth point clouds, video frames, and telemetry to perception and RL control modules.
- Build sensor fault detection, health monitoring, automatic recovery, dynamic re-connection, and runtime diagnostic daemons.
- Optimize Linux kernel driver stacks (V4L2, USB3/UVC, SocketCAN, Ethernet) for maximum throughput, sub-millisecond jitter, and minimal CPU footprint.
- Define unified sensor data abstractions, schema definitions, and ROS 2/DDS topic interfaces for seamless downstream algorithmic consumption.
- Collaborate with hardware and calibration engineers to conduct environmental stress validation and motion artifact testing on physical robot platforms.
- Produce clear technical documentation, integration standards, and automated testing suites for factory floor sensor testing.
Requirements:
- B.Sc. or M.Sc. in Computer Science, Robotics, Electrical Engineering, or related technical disciplines.
- 5+ years of software engineering experience in sensor integration, low-level driver development, or robotics middleware.
- Mastery of C++ (17/20) and Python with proven experience in object-oriented system design, multi-threading, and asynchronous I/O.
- Deep hands-on experience with sensor Linux drivers and communication protocols (V4L2, SocketCAN, SPI, I2C, MIPI-CSI2, GStreamer, OpenCV).
- Proven track record implementing sub-microsecond hardware time synchronization (PTP, PPS, external trigger pulses) across cameras and IMUs.
- Solid knowledge of ROS 2 / DDS pub-sub architecture, zero-copy shared memory transport, and system IPC optimization.
- Strong debugging skills using network tools (Wireshark), USB protocol analyzers, and GDB/Valgrind profiling suites.
Advantages:
- Direct experience integrating multi-modal sensor arrays on humanoid or quadruped robots.
- Experience with GPU acceleration for sensor stream decoding and pre-processing (CUDA, Jetson VPI, NvMedia).
- Experience with tactile sensor arrays, event-based cameras, or high-rate IMU filtering architectures.
- Comfortable communicating technical topics in English with international teams.