Shanghai
Full time
About us:
Mobileye is a global leader in Physical AI, developing computer vision, software, and hardware to power autonomous driving solutions and humanoid robots. Our mission is to bring autonomy into the real world by building intelligent technologies that are designed to expand accessibility and enhance everyday life, from advanced driver assistance systems (ADAS) and autonomous driving to robotics and humanoids.
Built on decades of automotive innovation and industrial-scale AI expertise, Mobileye technologies power more than 230 million vehicles worldwide. With teams around the world, we continue to innovate at the forefront of autonomous systems, advancing the next generation of Physical AI for the real world.
About the team:
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.
