Working Student (m/f/d) Post-Training, Evaluation and Benchmarking for Robotic Tasks

About the role

The AI Research Division of Agile Robots is looking for a Working Student (m/f/d) Post-Training, Evaluation and Benchmarking for Robotic Tasks. You will support the development of post-training, evaluation, and benchmarking workflows for learning-based robotic systems. The role focuses on making model behaviour measurable and comparable through structured experiments, reliable data preparation, and evaluation automation.

Your Responsibilities

• Data Analysis: Analyze robotic and learning-related data to understand quality, structure, and failure patterns, and support improvements to data collection workflows.
• Data Preparation: Prepare and organize datasets used for post-training, evaluation, and benchmarking of robotic models.
• Evaluation Design: Help define evaluation setups, benchmarks, and metrics that make model performance measurable across tasks and conditions.
• Experiment Execution: Run evaluation experiments, collect results, and support systematic comparison of models and configurations.
• Automation: Build and maintain Python-based scripts that reduce manual effort in evaluation and benchmarking workflows.
• Documentation: Present results to the team and document setups, observations, and findings in a clear and reproducible way.

Essential Skills

• Enrollment: Currently enrolled in a Bachelor's or Master's program in Computer Science, Robotics, Machine Learning, or a related technical field.
• Python: Strong Python skills and familiarity with common scientific computing libraries such as NumPy.
• Deep Learning: Solid understanding of deep learning fundamentals and familiarity with frameworks such as PyTorch.
• Experimentation: Ability to work in a structured way with experiments, results, and model comparisons.
• Version Control: Practical experience with Git and collaborative development workflows.
• Linux: Comfortable working in Linux-based development environments.
• Communication: Good written and spoken English and the ability to communicate findings clearly.

Beneficial Skills

• Robotics Context: Prior exposure to robotics systems, robot-learning workflows, or related dataset formats such as LeRobot.
• Model Development: Experience training or fine-tuning deep learning models in research or applied settings.
• Research Tooling: Familiarity with Docker or similar tooling used to support reproducible technical workflows.

What we offer

• Practical learning opportunities to complement your studies.
• 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.
• 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.