Field AI is transforming how robots interact with the real world by building risk-aware, reliable, and field-ready AI systems that address the most complex challenges in robotics, unlocking the full potential of embodied intelligence.
Requirements
- Strong C/C++ and Python; comfortable writing low-level embedded code (interrupts, DMA, drivers) and performance-aware control loops.
- Deep fundamentals in mechanics, dynamics, and multi-body dynamics (rigid-body kinematics, centroidal/whole-body dynamics, spatial algebra).
- Mastery of linear & state-space control (discrete-time design, LQR/LQG, observers), frequency-domain analysis, and stability/robustness proofs.
- Practical experience with model predictive control (formulation, constraints, warm-starts) and QP/OSQP/qpOASES/acados-style solvers.
- Proficiency in Kalman filtering and multi-sensor fusion; solid grasp of observability and noise modeling.
- System identification experience (grey-box/black-box, parameter estimation, excitation design, validation).
- Embedded platforms: MCUs, embedded Linux/RT-patched kernels, and at least one RTOS.
Responsibilities
- Control algorithms & real-time implementation
- Design, tune, and validate controllers (classical, modern/state-space, whole-body QP, MPC) for balance, locomotion, and manipulation.
- Implement high-rate control loops (≈100–1,000 Hz+) on embedded targets (MCUs and embedded Linux) with RTOS constraints, fixed-/floating-point trade-offs, and tight timing budgets.
- Estimation & system identification
- Build and deploy filters (EKF/UKF/ESKF) for IMU/encoder/vision fusion, contact estimation, and state reconstruction.
- Perform offline/online system identification of actuators and structures; parameterize friction/backlash/COM/inertia; maintain plant models that match reality.
- Create fast simulations (Python/NumPy; Drake/MuJoCo/Isaac Sim as appropriate) for controller bring-up and regression testing.
Other
- Degree in ME/EE/Robotics/CS (BS required; MS/PhD a plus) or equivalent hands-on experience.
- Comfortable with motor control and electromechanical systems (encoders, force/torque sensors); scopes/logic analyzers and hardware bring-up.
- Solid software practices: Git, code review, unit/integration testing, and reproducible experiment workflows.
- This is a fully onsite role, and candidates will be expected to work from our Mission Viejo, CA office.
- We are dedicated to fostering a diverse and inclusive workplace and encourage applicants from all backgrounds to apply.
