Dyna Robotics
Full-Stack Robotics Software Engineer
11mo ago
180000 –270000 USD / yearUSASeniorsoftware developmentroboticshardware-software integrationsensor fusionrobot controlteleoperation3d data visualization
Develop and own the end-to-end software stack for robotics, integrating AI models to physical actuators and ensuring reliable commercial-grade robotic performance.
Nice to have
- 2+ years working with physical robot hardware (arms, humanoids, or mobile manipulators).
- A history of building independent robotics systems (e.g., RoboMaster, FRC, or ambitious personal projects).
- Familiarity with computer graphics or 3D data visualization frameworks.
- Experience with imitation learning or robot learning pipelines.
- 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.
- As a Full-Stack Robotics Software Engineer , you will be the primary architect of the software "circulatory system" that connects our frontier models to physical actuators.
- This is a high-impact, dynamic role. You will own the end-to-end delivery of the robot’s software stack, from building the teleoperation interfaces and 3D data visualizers to debugging complex sensor-fusion issues on real hardware. You are the engineer who ensures that our AI research translates into reliable, commercial-grade robotic performance.
- End-to-End Delivery: Own the full software stack. You will rapidly develop clean, maintainable code for robot control, sensing, and remote teleoperation.
- Hardware-Software Integration: Lead the bringup, calibration, and integration of new sensors (LiDAR, Depth, IMU) and actuators. You’ll be the first line of defense in diagnosing complex SW/HW system-level issues.
- Infrastructure & Tooling: Architect backend services and APIs to support large-scale data collection. You will build the monitoring, logging, and evaluation tools that allow the AI team to verify model performance in real-time.
- 3D Visualization: Develop sophisticated tools for processing and visualizing geometric data, 3D rotations, and moving reference frames to help researchers "see" what the robot sees.
- Cross-Functional Velocity: Collaborate across AI, Controls, and Hardware teams to accelerate the path from a research hypothesis to a deployed robot capability.
- 5+ Years of Software Mastery: A proven track record of building highly reliable production software, with an emphasis on Python and C++.
- Geometric Intuition: Strong mathematical foundation in 3D geometry, rigid body transforms (SO(3)/SE(3)), and kinematics. You are comfortable using libraries like NumPy, SciPy, or Pinocchio.
- Full-Stack Proficiency: Experience building both backend services (REST APIs, Web Services) and the low-level software that interfaces with hardware SDKs or embedded systems.
- System Debugging: The ability to efficiently "bisect" a software stack to isolate bugs, whether they live in the network layer, the driver, or the geometric logic.
- Ownership & Drive: You feel at home testing code on electromechanical systems and have a "bias for action" when it comes to unblocking high-priority projects.