Controls Research Engineer

Join us to shape the next frontier of AI-driven robotics! Dyna Robotics makes general-purpose robots powered by a proprietary embodied AI foundation model that generalizes and self-improves across varied environments with commercial-grade performance. Dyna's robots have been deployed at customers across multiple industries. Its frontier model has the top generalization and performance in the industry. Dyna Robotics was founded by repeat founders Lindon Gao and York Yang, who sold Caper AI for $350 million, and former DeepMind research scientist Jason Ma. The company has raised over $140M, backed by top investors, including CRV and First Round. We're positioned to redefine the landscape of robotic automation. Join us to shape the next frontier of AI-driven robotics! Position Overview As a Controls Engineer, you are responsible for the robot’s neuromuscular system. You will bridge the gap between high-level AI reasoning and low-level motor torque, ensuring our semi-humanoids move with unprecedented fluidity, speed, and safety. This is a role for a modern controls expert who views "control" not just as a set of equations, but as the interface between learned policies and real-world physics. What You’ll Do Modern Whole-Body Control: Design and implement whole-body control (WBC) frameworks that produce stable, high-bandwidth motion for redundant, high-DOF semi-humanoid platforms. RL-to-Real Integration: Lead the deployment of learning-based controllers (RL, Imitation Learning) onto physical hardware. You will own the "Sim-to-Real" pipeline, ensuring learned behaviors translate into reliable, contact-rich robot interactions. Dynamic Characterization: Perform system identification and design calibration processes to characterize high-performance actuators and complex system dynamics. High-Fidelity Simulation: Build and optimize simulation environments (MuJoCo, Isaac, Pinocchio) to rapidly evaluate controller performance, stability margins, and failure modes. Hardware-Software Co-Design: Collaborate with hardware engineers to define the next generation of robot platforms by quantifying how latency, sensor noise, and mechanical design impact control performance. Interactive Tooling: Develop internal observability systems to visualize real-time control behavior, helping the broader AI team understand the physical impact of their models. What You’ll Bring MS or PhD in Robotics/Controls: Or equivalent "in-the-trenches" experience building high-performance robots. Modern Toolkit: Deep understanding of rigid body kinematics, spatial math (SO(3) / SE(3)), and dynamics libraries (e.g., Pinocchio, Drake, or MuJoCo). AI-First Mindset: Proven experience with Reinforcement Learning or Imitation Learning for manipulation or locomotion. You know how to wrap a learned policy in a robust safety layer. Real-Time Mastery: Proficiency in C++ and Python for latency-sensitive workloads running on edge compute. Hands-on Grit: A track record of pushing physical hardware to its limits—faster movements, tighter stability, and better disturbance rejection.