Dyna Robotics
Controls Research Engineer
5mo ago
180000 –290000 USD / yearUSASeniorreinforcement learningroboticscontrol systems
Engineer responsible for designing and implementing whole-body control frameworks for semi-humanoid robots, bridging AI reasoning and motor control.
Nice to have
- Experience with Hybrid Motion-Force Control (Operational Space Control, Inverse Dynamics).
- Deep understanding of low-level motor driver architectures and EtherCAT/CAN communication.
- A portfolio of publications at RSS, CoRL, or ICRA showcasing state-of-the-art robot learning or control.
- At Dyna Robotics , we build technology for the real world, which requires a team as diverse as the environments our robots inhabit. We are an equal opportunity employer committed to technical rigor and mutual respect.
- Don’t let a checklist stop you. Data shows that underrepresented groups often only apply if they meet 100% of the criteria. We value problem-solving and grit over keyword matching. If you’re passionate about the intersection of geometry and robotics, we want to hear from you—even if you don't check every box.
Other
- 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!
- 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.
- 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.
- 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.