Controls Research Engineer

Company Overview:

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!

Learn more at dyna.co

Position Overview:

As a controls researcher at Dyna Robotics, you will be responsible for ensuring that our robots take full advantage of their actuators. You will lead design, testing, and implementation of control algorithms that leverage all available information to allow the most dynamic motion possible. You will also develop tools to make controls research easier, and allow larger parts of the team to understand the impact of control on the overall performance of the robot. You will collaborate closely with robotics engineers, AI researchers, and hardware engineers to ensure optimal performance of our overall system.

Key Responsibilities:

• Design, implement, and tune control algorithms for semi-humanoid robots, with emphasis on learning-based approaches (RL, imitation learning, adaptive control)

• Build high-fidelity simulations and benchmarks to rapidly iterate on controller and policy performance

• Analyze actuator dynamics and sensor data to get the most out of our motors

• Create internal tools that help the broader team visualize and understand control behavior

• Collaborate with hardware engineers on actuator selection, sensor integration, and mechanical design trade-offs

• Work with AI/ML researchers to connect learned behaviors to low-level motor control

• Document methods so insights scale across the organization

Qualifications:

• MS or PhD in robotics, controls, machine learning, or a related field

• Experience with learning-based control (e.g. reinforcement learning, imitation learning)

• Strong foundation in classical control (PID, LQR, MPC) and state estimation

• Proficiency in C++ and Python; experience with real-time systems

• Experience deploying controllers or learned policies on physical hardware

• Familiarity with simulation tools (MuJoCo, Isaac Sim, Drake, or similar)

• Strong communication skills and ability to work across teams

Preferred Qualifications:

• Deep interest in pushing dynamic performance—faster movements, higher bandwidth, better stability margins

• Track record of publications in robot learning, robotic manipulation, or humanoid control

• Experience with low-level motor drivers

• Prior work at a robotics startup