GRAM is a self replication company creating populations of insectoids for the physical economy.
Our first research frontier is self-preservation: the base case of physical self-replication. Our machines will survive, coordinate, and recover without humans. We believe scalable machine labor requires more than single-agent task generality or machines shaped in our image.
About the roleYou will build the real-time control architecture that coordinates an insectoid's full body across changing geometry, orientation, contact, load, and machine state. The work spans dynamics, contact constraints, force allocation, trajectory tracking, actuator limits, transitions, disturbance rejection, and recovery, carried through production C++ and onto hardware. You will develop the control-oriented models, system-identification methods, and hardware-in-the-loop environments needed to build and validate the controller, then establish its measured operating envelope on the physical machine.
What you will do- Design whole-body controllers that coordinate motion and contact forces across coupled degrees of freedom.
- Implement real-time control software in C++ with explicit timing, numerical stability, saturation, and fault behavior.
- Develop control-oriented dynamics models, system-identification experiments, and actuator characterizations that improve controller fidelity.
- Integrate state estimation, trajectory generation, manipulation, embedded systems, and safety logic into one testable control path.
- Define quantitative envelopes for tracking error, contact stability, disturbance rejection, transition success, compute latency, and recovery.
- Build controller simulations, hardware-in-the-loop tests, and physical-machine tests that reproduce failures and prevent regressions.
- Use test evidence to distinguish controller defects from estimation error, unmodeled dynamics, actuator limits, and mechanical faults.
- Document model validity and confirm simulated results on physical hardware.
- Bachelor's degree in mechanical engineering, electrical engineering, robotics, controls, applied mathematics, or a related field, or equivalent practical experience.
- Demonstrated experience developing feedback control for a multi-degree-of-freedom robot, vehicle, aerospace platform, or other nonlinear physical system.
- Strong C++ and Python skills and command of rigid-body dynamics, linear systems, optimization, and numerical methods.
- Hands-on experience with a controls or dynamics stack such as Drake, Pinocchio, MuJoCo, ROS 2 control, Eigen, or an equivalent internal framework.
- Deployed a controller on physical hardware and can present measured tracking, stability, latency, or disturbance-rejection results plus a failure that required redesign.
- Whole-body control, model predictive control, inverse dynamics, contact optimization, or legged robotics.
- Real-time Linux, deterministic communications, actuator torque control, or safety-rated motion systems.
- Controls deployed in aerospace, autonomous vehicles, industrial robotics, or field robotics.
- Gait mechanics and discrete state estimation
- Footstep planners in complex environments
- Elevation mapping and perception integration
- Direct HW tuning for repetitive impact
The annual base salary range for this Palo Alto position is $150,000–$250,000+. Health coverage, benefits, and generous equity come with the role. This role is on-site in Palo Alto. A relocation bonus is available. We hire to start as soon as possible. We review what you’ve shipped; if it’s the caliber we seek, interviews take about a week, start to finish. We treat your work and conversations with discretion.
