Utilization of Physical AI for Fast and Efficient Implementation of Robotic-Assisted Processes in Di

At Roche you can show up as yourself, embraced for the unique qualities you bring.

Our culture encourages personal expression, open dialogue, and genuine connections,  where you are valued, accepted and respected for who you are, allowing you to thrive both personally and professionally.

This is how we aim to prevent, stop and cure diseases and ensure everyone has access to healthcare today and for generations to come.

Join Roche, where every voice matters.

The Position

About the project:

The implementation of robotics and automation in industrial environments currently requires high investment, significant engineering effort, and extensive setup times.

Consequently, automation is often only economically viable for processes characterized by high repetition, low uniformity, low variance, or strict requirements for product and personal protection.

This PhD project aims to drastically reduce the implementation effort and associated costs of robotic systems.

By lowering these barriers, automation can become viable for flexible, low-volume, and high-variance production environments.

The core focus of this research is the utilization of Physical AI for fast, intuitive, and efficient training and adaptation of robots.

The project will evaluate key factors required to achieve effortless implementation while simultaneously ensuring high process robustness and safety.

Degree: Master’s degree (or equivalent) in Robotics, Computer Science, Mechanical/Electrical Engineering, Automation Engineering, Physics, or a closely related field.

Your tasks and responsibilities:

Physical AI & Machine Learning:


* Solid understanding of Machine Learning (ML) and Deep Learning (DL) architectures


* Familiarity with concepts like Reinforcement Learning (RL), Imitation Learning (Learning from Demonstration), or Physics-Informed Neural Networks (PINNs)


* Experience applying AI to physical systems or hardware

Robotics & Automation:


* Strong foundation in robot kinematics, dynamics, and control


* Experience with robotic frameworks, primarily ROS / ROS2 (Robot Operating System)

Software Engineering:


* Advanced programming skills in Python and/or C++.Experience with ML frameworks such as PyTorch, TensorFlow, or JAX.Familiarity with simulation environments (e.g., Isaac Sim, MuJoCo, Gazebo)


* Domain Knowledge & Soft Skills

Industrial Application: Basic understanding of production environments, ideally regarding process safety, robustness, or flexible manufacturing (low-volume, high-variance)

Regulated Environments: Interest in or prior exposure to strict production standards (like cleanrooms or pharmaceutical/diagnostic constraints) is a strong plus

Analytical Mindset: Ability to bridge abstract AI theory with practical, real-world robotic deployment

Communication & Collaboration: Strong team player capable of working in interdisciplinary teams and presenting research at international conferences

Your Advantages: 


* 3,75...