Robotic Foundation Model Application Engineer

Shape the Future of Human-Robot Collaboration

In the Software Department, you're shaping robotic solutions that redefine human-machine collaboration. You'll work with cutting-edge technology, setting industry-changing standards. Not only will you help develop our solutions, but you'll also set new trends and drive innovations forward. In an agile and interdisciplinary team, you'll engage in exciting projects. With clear Scrum processes like daily stand-ups, sprint planning, and reviews, you remain flexible and efficient. Collaborating closely with other departments allows you to create software solutions that are both technically advanced and practically effective. Here, you'll find an environment where creativity and technological excellence go hand in hand. If you're eager to turn ideas into reality and enjoy taking technology to the next level, the Software Development Team at NEURA offers the perfect challenge for you.

Launch and Shape a RoboGym

NeuraGym is our physical AI training center, where we collaborate with our partners to gather extensive data and teach robots at scale. It serves as the infrastructure where applications are developed for all our robots - from our cognitive robots arm MAiRA to our humanoid 4NE-1 and our service robot MiPA.

As a Robotic Foundation Model Application Engineer at NeuraGym, your role is to consult users as they build applications within this infrastructure. You guide them through the entire process, starting from the initial concept of their dataset to the creation of a validated skill that operates seamlessly on real hardware.

Your mission & challenges

• Act as AI consultant for NeuraGym users: scope feasibility, choose algorithms, plan data collection
• Onboard users to the full NeuraGym pipeline: teleoperation, annotation, training, simulation, deployment and validation
• Collaborate closely with the on-site Robotics Engineer during data capture and experiments to ensure that the desired behavior and safety standards are achieved
• Advise users while they debug: review training scripts, point out data issues, help reproduce model bugs; step in hands-on when a blocker persists
• Serve as a valuable interface to our cloud team and AI team, facilitating collaboration and support where needed
• Feed lessons learned back into both the NeuraGym product roadmap and the Neura core AI roadmap

What we can look forward to

• Master’s degree in Computer Science, Robotics, Electrical Engineering or related field
• 3+ years hands-on machine-learning experience in robotics - strong in at least one of: vision-based manipulation, reinforcement/imitation learning, or multimodal models - and keen to learn the rest
• Solid Python skills (C++ a plus); practical experience with PyTorch or TensorFlow
• Comfortable working directly with real robot hardware and associated middleware
• Cloud experience (AWS, Azure, or GCP) and experience with robotic simulation tools (IsaacSim, MuJoCo, etc.) is a plus
• Proven problem-solving abilities and ability to handle multiple projects in parallel
• Clear communicator who can translate between researchers, engineers and end-users. You have a good command of English and German language (B2 - C1 level)