Controls Engineer

About REVEL

REVEL is an AI robotics company developing physical intelligence for general-purpose humanoid robots. We capture the force, dexterity and intent of human work with our Neural Gambit wearable, and use it to train RAI, the intelligence that powers our robots. REVEL is headquartered in Palo Alto, California, with R&D and engineering facilities in Prague and Hradec Králové, Czech Republic. This role is on-site with our engineering team in the Czech Republic.

Own low-level control of GENESIS arms and hands.

Responsibilities

Design, implement, and tune control algorithms (PID, cascaded loops, LQR, MPC, or nonlinear control) for real robotic hardware

Model robot dynamics and kinematics to inform controller design and validate performance against real-world behavior

Take controllers from simulation to physical hardware, anticipating and mitigating the differences between the two

Debug control instability, timing/latency issues, and hardware-software integration problems end-to-end

Design and tune state estimation and sensor fusion pipelines that feed closed-loop control

Collaborate with software, mechanical, and electrical engineers to integrate control systems into the broader robot stack

Validate control performance through structured testing on hardware, and iterate based on results

Document control architectures, tuning parameters, and known limitations for the rest of the team

Requirements

3+ years of relevant professional experience

Deep expertise in control theory (PID, state-space, LQR, MPC, or nonlinear control) and the judgment to choose and design the right approach for a given system

Proven experience designing controllers for real robotic hardware, not just simulation—including tuning for stability, robustness, and performance under real-world disturbances

Strong understanding of robot dynamics and kinematics (rigid body dynamics, Lagrangian/Newton-Euler formulations, contact dynamics where relevant)

Professional experience with ROS/ROS2 and real-time or near-real-time control loops on embedded or industrial hardware

Real experience in force control.

Strong C++ and Python skills for control-relevant, performance-critical code

Experience with state estimation and sensor fusion (Kalman filters, EKF/UKF, or observer design) for closed-loop control

Comfortable debugging control instability, timing/latency issues, and hardware-software integration problems end-to-end

Bonus qualifications

Experience with whole-body control, legged locomotion, or highly dexterous/manipulation systems

Familiarity with trajectory optimization, motion planning, or optimal control frameworks

Experience with sim-to-real transfer and hardware-in-the-loop testing

Background integrating learned policies (RL, imitation learning) with classical control stacks

Familiarity with real-time operating systems or deterministic scheduling (RTOS, PREEMPT_RT)

Publications, patents, or strong open-source contributions in controls, robotics, or dynamical systems

Why REVEL

Work That Ships : We capture how skilled humans work, their force, touch, and judgment, and our robots do the work. You put robots on a paying customer's floor, not in a demo loop

The Team: Colleagues from NVIDIA, SpaceX, and Neura Robotics, and founders you work with directly. No layers, no process between you and the decisions

Your Own Hardware : A top-spec GPU workstation, cluster access, and hands-on time with the robots you're building. Not a software sandbox

Keep Learning : Conference budget for select roles (GTC, CoRL, ICRA), and room to publish and contribute to open source where our IP allows

What we offer

Unlimited Paid Time Off : Real flexibility to take time away when you need it. We trust our people to own their work, their time, and their results

Prague, On-Site : Robots need hands, so we work together in our Prague lab. Moving here? We sponsor your work visa and cover relocation

Lunch, On Us : Complimentary lunch every working day, plus coffee, snacks, and drinks whenever you need a boost

How to apply

Apply through the link on this posting.