Robotics Software Engineer (m/f/d)
As a Robotics Software Engineer with an intelligent application focus at Agile Robots, you will design, implement, and tune the controllers that produce smooth, safe, and accurate motion on our robots — impedance, position, admittance, and force control, as well as whole-body and optimal control. You will identify the dynamic models these controllers rely on and close the sim-to-real gap, so that behavior validated in simulation performs reliably on physical hardware.
- Design, implement, and tune real-time controllers — impedance, position, admittance, and force control — for smooth, safe, and accurate robot motion
- Develop whole-body control and trajectory-optimization algorithms (MPC, DDP/iLQR, QP-based control) for manipulation and/or legged systems
- Perform system identification and calibration: dynamic parameters, actuator and friction models, sensor and vision calibration, and state estimation
- Build and validate simulation pipelines and reduce the sim-to-real gap
- Deploy and validate controllers on real hardware against performance and safety requirements
- Write clean, performant, well-documented C++ and Python code
- Collaborate with learning, perception, and hardware teams to integrate control into the wider system
- Master's or PhD in Robotics, Control, Applied Mathematics, Electrical Engineering, Computer Science, or a related field — or a Bachelor's with equivalent hands-on experience
- Solid experience in control for articulated robots (e.g. impedance, position, admittance, force, or whole-body control)
- Strong grounding in rigid-body dynamics and control theory
- Numerical optimization for control: nonlinear programming, MPC, DDP/iLQR, QP solvers
- System identification and state estimation (parameter identification, calibration, Kalman filtering)
- Proficiency in C++ and Python
- Experience deploying controllers on real robots (manipulators, legged, or humanoid)
- Strong problem-solving and communication skills
- Experience integrating learned policies (e.g. reinforcement learning) with model-based control
- Familiarity with simulation tools such as MuJoCo, NVIDIA Isaac Sim, or similar
- Experience with the optimal-control / dynamics stack (e.g. Pinocchio, Crocoddyl, CasADi, OSQP)
- GPU acceleration (CUDA); real-time operating systems and hardware interfacing
- Open-source contributions to robotics control or dynamics libraries
- A dynamic high-tech company combined with financial soundness and world-class investors.
- Join an interdisciplinary, international team with 60+ different nationalities in a collaborative work environment.
- Lots of development opportunities in the context of our continued growth.
- Challenging tasks and impactful projects alongside experts that enable professional and personal growth.
- Corporate Benefits Program that covers health, mobility, and learning with 100€ net per month.
- Modern office facilities with a rooftop terrace overlooking Munich, free drinks & fruits, and regular company events contribute to a good working environment.