Data Science & Robotics Machine Learning Internship

About the role

We are looking for an intern to join our Robotics Machine Learning Engineering team in Berlin. You will help turn remote‑controlled hardware into autonomous robots by building and fine‑tuning training pipelines for vision‑language‑action (VLA) models and reinforcement‑learning agents.

Key responsibilities

• Design and implement data pipelines for teleoperation data collection and analysis.
• Fine‑tune open‑source and partner VLA models using Python and deep‑learning frameworks.
• Manage large datasets required for model training and oversee teleoperation activities.
• Apply reinforcement‑learning techniques to improve robot manipulation tasks.
• Use high‑fidelity simulators (MuJoCo, NVIDIA Isaac Sim, Omniverse) for sim‑to‑real testing before deployment.

Required profile

• Currently pursuing a Master’s or PhD in Robotics, Computer Science, Data Science, AI or a related field.
• Hands‑on experience with robotics and embodied AI.
• Strong proficiency in Python and at least one deep‑learning framework (PyTorch, TensorFlow, or JAX).
• Familiarity with Transformers and VLA architectures is a plus.
• Proven experience with physics‑based simulators such as NVIDIA Isaac Sim, MuJoCo or Gazebo.
• Ability to work with large datasets, automate cleaning and build training pipelines.
• Fluent English.

Required skills

• Python
• PyTorch
• TensorFlow
• JAX
• Transformers
• VLA architectures
• Reinforcement Learning
• NVIDIA Isaac Sim
• MuJoCo
• Omniverse
• Data engineering for large datasets

What we offer

• Potential full‑time offer after a successful internship.
• In‑person work in our downtown Berlin office.
• Access to cutting‑edge robotics hardware and software.
• Opportunity to impact real manufacturing projects.