Embedded Systems Engineer, Humanoid Robotics

About Us

Field AI is transforming how robots interact with the real world. We are building risk-aware, reliable, and field-ready AI systems that address the most complex challenges in robotics, unlocking the full potential of embodied intelligence. We go beyond typical data-driven approaches or pure transformer-based architectures, and are charting a new course, with already-globally-deployed solutions delivering real-world results and rapidly improving models through real-field applications.

Embedded Systems Engineer

In this role you will develop computing systems for humanoid robots. This may span compute platform design (ARM, SoC, microcontrollers), firmware and BSP bring-up, and kernel-level Linux work. Work will focus on a robot payload that intakes LiDAR, camera, IMU, and tactile sensor information and then outputs joint manipulation and locomotion commands that let the robot stand, move, and use its hands. 

You will partner closely with the ML team building the robot's software brain, ensuring the compute platform can run their perception and manipulation models with the latency and throughput they need. The system is designed to operate across a diversity of humanoid robot platforms, so your work will generalize across different hardware rather than target a single robot. You will collaborate closely with the mechanical, electrical, and ML teams to build tightly integrated, safety-conscious solutions ready for deployment in the field. 

What You Will Get To Do

1. Backpack Compute Platform

• Compute Platform Design: Design and select the embedded compute platforms (ARM, SoC, microcontrollers) that power the humanoid payload, balancing capabilities against SWaP constraints.

• Firmware & BSP Bring-Up: Write and customize bare-metal and RTOS firmware, board support packages (BSPs), and bootloaders for the humanoid payloads computing hardware.

• Kernel-Level Development: Work at the Linux kernel level to support real-time performance and reliable operation of the backpack's compute stack.

• Testing & Diagnostics: Conduct thermal profiling, power draw analysis, and latency measurement, and implement watchdogs and health checks for the compute stack.

2. Sensor & Actuator Drivers

• Perception & State Sensor Drivers: Adapt, integrate, and where needed develop drivers for cameras, LiDAR, and IMUs that feed the backpack's compute platform with real-time perception and state-estimation data.

• Motor, Joint & Tactile Drivers: Adapt, integrate, and where needed develop drivers for motors, joint actuators, and tactile sensors, supporting low-latency control and feedback for humanoid manipulation and locomotion.

• Communication & Timing: Bring up wired (Ethernet, CAN, GMSL, SPI, I2C) and wireless interfaces with deterministic timing (PTP, PPS) across the payload.

3. Manipulation & ML Integration

• ML Team Partnership: Partner closely with the ML team building the robot's software brain to ensure the compute platform meets their latency, memory, and throughput needs.

• Manipulation Data Pipeline: Build the data pipeline connecting camera, LiDAR, IMU, and tactile input to joint manipulation commands, from raw sensor capture through to actuator control.

• Edge ML Enablement: Support accelerated inference on the backpack so ML models can interpret sensor data and issue robot commands in real time.

• ROS/DDS Middleware: Expose driver and sensor data through ROS/ROS2 and DDS interfaces so the ML team's software brain can consume it in real time.

4. Cross-Platform Generalization & Collaboration

• Platform Abstraction: Design the backpack's compute and software architecture to generalize across a diversity of humanoid robot platforms.

• Cross-Team Collaboration: Work closely with mechanical, electrical, and sensor engineers to develop a tightly integrated backpack payload.

• Technical Leadership: Lead the technical direction of backpack compute development, from architecture decisions through implementation.

• Safety & E-Stops: Implement e-stop circuitry and safety monitoring on the backpack platform, laying the groundwork for functional safety as the fleet matures.

What You Have

• Education: B.S., M.S., or Ph.D. in Computer Engineering, Electrical Engineering, Robotics, or a related field.

• Experience Level: Minimum of 3+ years of hands-on experience with embedded systems.. We welcome candidates across mid-level to senior and staff levels.

• Programming: Proficient in C++ and Python for embedded and application-level development.

• Embedded Systems Experience: Experience bringing up and customizing bare-metal and RTOS firmware, Linux kernel and device drivers, and board support packages (BSPs), across platforms such as Jetson or custom SBCs.

• Driver Development: Experience developing drivers for cameras, LiDAR, IMUs, tactile sensors, or motors, connecting sensors and actuators to embedded compute.

• ML/Edge Acceleration: Familiarity with GPU, TPU, or NPU offload and frameworks such as CUDA or TensorRT for edge inference, ideally supporting manipulation or perception models.

• Real-Time Communication Protocols: Hands-on experience with Ethernet, CAN/CAN-FD, SPI, I2C, UART, USB, or PCIe, wireless links, and timing protocols such as PTP.

• ROS & Middleware: Familiarity with ROS/ROS2 and DDS for exposing sensor and actuator interfaces to higher-level software.

• SWaP-Constrained Design: Experience designing compute hardware and firmware under tight size, weight, and power (SWaP) constraints, such as wearable or backpack-style payloads.

What Will Set You Apart

• Humanoid Robotics Experience: Experience developing embedded systems, firmware, or drivers for humanoid or other legged robot platforms.

• Manipulation & Robot Control Knowledge: Familiarity with joint manipulation, motor control, and how sensor data flows into robot commands such as standing or grasping.

• Kernel-Level Development: Experience with Linux kernel modules, device driver development, kernel-level debugging, PREEMPT_RT, and deterministic, low-jitter timing in production systems.

• Safety-Critical Systems: Experience implementing e-stop circuitry, safety monitoring, or other safety-critical embedded systems for robots operating near people. Experience with functional safety standards such as ISO 13849 or ISO 10218 for robots operating in human environments.

• ML Collaboration: Experience working directly with ML or perception teams to meet model latency, memory, and throughput requirements on embedded hardware.