Robotics Control Engineer (Locomotion)

Job Description

Seer is working with one of the most technically ambitious robotics companies in the world — developing humanoid robots capable of dynamic, adaptive movement in the real world. Backed by top-tier investors and led by pioneers in AI, controls, and robotics, this team is pushing beyond the frontier of what legged machines can do.

As part of this growth, they’re hiring Robotics Control Engineers with deep expertise in locomotion, reinforcement learning, and dynamic control systems to join their R&D headquarters.

The Role:

You’ll design and implement locomotion control policies — from walking and stair climbing to fall recovery and manipulation-balanced motion. You’ll work at the intersection of classical control theory and reinforcement learning, deploying your work on humanoid platforms in the wild.

Key Details:

• Location: Hybrid or Onsite – US or EU HQs
• Salary: Highly competitive + equity + relocation support
• ⚙️ Tech Stack: Python, C++, Mujoco, Isaac Sim, MPC, RL, ROS2, custom hardware
• Robots: Full-size humanoid platforms with real-world deployment targets
• Domains: RL for locomotion, whole-body control, balance optimization, sensor fusion

What You’ll Do:

• Develop and implement control algorithms (classic or RL-based) for complex locomotion tasks — including walking, squatting, stair climbing, fall recovery, and manipulation-aware balancing.
• Model and simulate advanced robot dynamics, incorporating actuator limitations, contact physics, and kinematic constraints.
• Perform robust testing across simulation (Mujoco, Isaac Sim) and real hardware environments, optimizing for stability, speed, and energy efficiency.
• Work across perception, software, and mechanical engineering teams to integrate and refine locomotion control within full-stack systems.

What We’re Looking For:

• Master’s or PhD in Robotics, Control Systems, Mechatronics, or similar
• 2+ years experience in control systems for biped or humanoid robots
• Strong understanding of:
• Model Predictive Control (MPC), optimal & feedback control
• Reinforcement learning in physical systems
• Humanoid dynamics, balance control, and full-body coordination
• Proficiency in Python and C++ for real-time algorithm development
• Experience with hardware-in-the-loop testing and sim-to-real deployment
• Simulation skills with tools like Mujoco, Isaac Sim, or equivalents
• Experience with model-free RL, imitation learning, or hybrid controllers blending learning and classical methods

Nice to Have:

• Familiarity with real-time control systems and low-level hardware integration
• Sensor fusion knowledge (IMUs, joint encoders, force/torque sensors)
• Deep understanding of actuator modeling and dynamics
• Experience in gait optimization, compliance testing, and energy evaluation
• Knowledge of balance techniques like ZMP, capture point, and whole-body control strategies

This is a rare opportunity to shape the motion and intelligence of real-world humanoid systems — working on some of the hardest and most exciting challenges in robotics today. If you're passionate about making machines move like living beings, this is your moment