Figure is an AI robotics company developing autonomous general-purpose humanoid robots. The goal of the company is to ship humanoid robots with human level intelligence. Its robots are engineered to perform a variety of tasks in the home and commercial markets. Figure is based in San Jose, CA and require 5 days/week in-office collaboration.
We are seeking a Hands Actuator Controls Engineer on the Actuation/Hand Integration team to develop and optimize the control systems of our humanoid robot hand actuators, to enable precise, smooth and safe motion. This role will design multi‑degree‑of‑freedom position and force controllers, and sensor‑fusion algorithms to enable dexterous manipulation. The engineer will also address practical issues like bumpless mode transitions, actuator saturation and system linearization, ensuring high performance across all operating modes.
Key Responsibilities:
- Architect multi-DOF controls: design scalable, high-performance, robust controls of hands actuators to enable AI policies to achieve human-like dexterity of the hands and object manipulation, using both torque‑based and position‑based strategies
- Implement force control: Develop algorithms to enable grasp-force control, active shock isolation and impedance/admittance control.
- Implement state machines for transitions: Create control state machines for bump-less mode changes and handle saturation/anti‑windup
- Design sensor‑fusion and state estimation for pinch, slip or impact detection algorithms.
- Create diagnostics and fallback strategies: Build real‑time diagnostics, monitoring and fallback modes to maintain safe operation in every condition.
- Model, test and correlate: Develop numerical models of the hand system and perform test/model correlations to validate and tune control algorithms
- Deploy at scale: Implement robust techniques that handle variations across a large fleet in diverse environments.
- Accelerate design iteration: Provide feedback to mechanical, motor, electrical, firmware and sensing teams through trade‑off studies, simulations and subsystem testing
- Collaborate across disciplines: design control interfaces in collaboration with AI teams for data collection and for policy evaluation.
Requirements:
- Extensive Experience: At least 10 years of hands‑on work with robotic or actuation systems, with a proven record of designing high‑performance control architectures for complex, multi‑DOF systems.
- Control expertise: Deep knowledge of motion and force control (including admittance/impedance control and vibration/shock isolation) and experience conducting actuation trade studies.
- Software proficiency: Strong C++ and Python skills; comfortable developing on Linux‑based systems
- Theoretical foundation: Solid grounding in mechanics, kinematics, dynamics, control theory and sensor technologies, with familiarity in managing mode transitions and anti‑windup/saturation strategies.
- Hands-on approach: capability to rapid-prototype, test and deploy robust solutions at scale
- Education: Master’s or PhD. degree in Mechanical, Electrical/Controls Engineering, Robotics or a related field.
Bonus Qualifications:
- Prior work on robotic hands actuation systems or multi DOF systems.
- Prior expertise working with MIMO systems.
- Prior Expertise deploying control systems on a large fleet of systems.
The US base salary range for this full-time position is between $150,000 and $300,000 annually.
The pay offered for this position may vary based on several individual factors, including job-related knowledge, skills, and experience. The total compensation package may also include additional components/benefits depending on the specific role. This information will be shared if an employment offer is extended.