Robot Machine Learning Engineer (Werkstudent*in) - Humanoid Robotics Startup

Below are some of the core focus areas for Machine Learning Engineers at RoboService:

• Collect & curate teleoperation datasets (RGB/Depth + proprioception + force/torque): define schemas, ensure time sync (PTP/NTP), and set quality gates.
• Train and evaluate imitation-learning / diffusion policies (PyTorch) for manipulation; stand up baselines and compare against strong references.
• Build fast simulation loops (Isaac Sim/Gym or Gazebo) for augmentation and rapid iteration; apply domain randomization for Sim2Real.
• Optimize inference on robot (TorchScript/ONNX/TensorRT) with latency/throughput targets on Jetson/x86.
• Integrate policies into ROS 2 nodes; define safe fallbacks, gating, and E-stop pathways with controls teammates.
• Explore Vision-Language-Action approaches for task generalization and evaluation.

Tech stack you'll touch

PyTorch (Lightning/Hydra) · Python (+ some C++ helpful) · ROS 2 (Humble/Jazzy) · Isaac Sim/Gym or Gazebo · CUDA/cuDNN · ONNX/ONNX Runtime/TensorRT/TorchScript · W&B/MLflow · DVC · OpenCV · Open3D · NumPy/Pandas · Git/GitHub (Actions/CI) · Jetson Orin/x86 · basic MoveIt 2 & PCL a plus.

Do you have experience in Python?, * Demonstrated interest and aptitude for working at the intersection of hardware and software.

• Experience training at least one imitation-learning (BC), RL, or diffusion model (course, lab, or personal project) in PyTorch and evaluating it with clear metrics.
• Practical ROS 2 experience and one simulator (Isaac Sim/Gym or Gazebo).
• Comfortable with rosbag, camera calibration, Linux dev, and reading research to implement baselines.
• High level of creativity and desire to implement your ideas
• Availability of 20 hours per week during the semester; 40 hours during semester breaks.

Nice to Have:

• TensorRT/ONNX deployment on Jetson, latency budgeting, or custom CUDA kernels.

• MoveIt 2, grasp planners, point-cloud ops (PCL).

• EKF/UKF, learned visual encoders, or VLA experience.

• Experiment tracking at scale (W&B/MLflow) and dataset mgmt (DVC).

What You Can Look Forward ToCreative Freedom and Agility

Enjoy a dynamic, self-reliant work culture with flat hierarchies and flexible hours. Ideal for motivated students seeking an inspiring professional setting to apply their skills in a fast-moving robotics environment.

Passion for Winning

Join a passionate and highly skilled international team aiming to redefine the future of robotic assistants.

Attractive Compensation

Benefit from a competitive student salary along with exclusive employee discounts.

One Team

Whether it's a summer party or company town hall meeting, we celebrate our successes together.

Professional Growth

Access to continuous learning opportunities, mentorship, and support for your personal and professional development.

Gehalt: 18,00€ - 30,00€ pro Stunde

Erwartete Arbeitsstunden: mindestens 20 pro Woche

Arbeitsort: Vor Ort     If you require alternative methods of application or screening, you must approach the employer directly to request this as Indeed is not responsible for the employer's application process.