At XDOF, we're at an inflection point. Frontier labs are racing to build general-purpose robots, and high-quality training data is the bottleneck. We're building the foundation behind the foundation models — the data collection systems, operational capability, exabyte-scale data warehouse, and software toolchain — to help our partners drive the field forward.
Great data starts with great hardware behavior. We're looking for a Robotics Controls Engineer to build the high-performance control systems that make our dexterous manipulators and humanoid robots move safely, precisely, and repeatably — because every teleoperation session, every collection run, and every downstream model depends on robots that respond exactly as commanded.
What You'll Do
Controls engineers are the bridge between robot hardware and reliable, high-quality motion. Sample projects include:
implementing joint-space and Cartesian impedance / torque control for 7+ DoF robotic arms
building whole-body control (WBC) for highly redundant humanoids with mobile bases, arms, and actuated torsos
designing optimization-based controllers: QP formulations, inverse dynamics, task/null-space control, and redundancy resolution
developing collision-aware motion and control, including self-collision avoidance and environment constraints
implementing and integrating real-time control software on physical robots, from simulation through hardware deployment
tuning and validating controller performance across diverse manipulation and locomotion tasks
working closely with data collection operators and hardware teams to diagnose and resolve control-related failure modes during teleoperation and autonomous runs
About You
Baseline skills:
bachelor's or master's degree (or equivalent experience) in robotics, mechanical engineering, electrical engineering, computer science, or a related field
strong fundamentals in robot dynamics, kinematics, and feedback control
hands-on experience implementing controllers on real robotic systems, not just in simulation
strong C++ and/or Python, and comfort working with real-time robotics systems
You might be a good fit if you:
have experience with whole-body control, operational-space control, MPC, or optimization-based control
come from a background in humanoid robotics, manipulation, legged robotics, or advanced industrial robot control
have worked on real-time embedded control software and understand the constraints of deploying to physical hardware
are very comfortable working in 0→1 environments
are mission-driven and passionate about robotics: work at XDOF is fast-paced and constant. We hope you love what you're going to be doing, because you'll be doing a lot of it!
