Utilization of Physical AI for Fast and Efficient Implementation of Robotic-Assisted Processes in Diagnostic and Pharmaceutical Raw Material Production (m/f/d)

F. Hoffmann-La Roche AG; Penzberg; On-site; EUR 38,000 - 46,000; Full time

Benefits offered by this job

Roche Boarding House

Transport connections to Munich via Ro

Roche Shuttle

Job summary

Roche invites applications for a PhD project in robotics and automation to reduce implementation effort and costs using Physical AI. The project focuses on fast training, robust deployment, and safe operation in industrial environments.

The candidate will apply ML/DL, RL, and PINNs with ROS/ROS2, PyTorch/TensorFlow, and physics-based simulations. Start: Jan 2027 for 3 years, with accommodation options and Roche Shuttle transport.

Qualifications

• Master’s degree in Robotics, CS, Mechanical/Electrical Engineering, Automation Engineering, Physics or related field.
• Experience with ML/DL architectures and AI for physical systems.
• Familiarity with ROS/ROS2 and robot frameworks.
• Proficiency in Python and/or C++.
• Experience with ML frameworks and simulation environments.

Responsibilities

• Physical AI & ML: solid understanding of ML/DL architectures; RL, Imitation Learning, PINNs; AI for physical systems/hardware.
• Robotics & Automation: knowledge of robot kinematics, dynamics, and control; ROS/ROS2.
• Software Engineering: programming in Python and/or C++, ML frameworks (PyTorch, TensorFlow, JAX); simulators (Isaac Sim, MuJoCo, Gazebo).
• Domain Knowledge & Soft Skills: understanding production environments, process safety, robust/flexible manufacturing.
• Regulated Environments: exposure to cleanrooms or pharma/diagnostic constraints is a strong plus.
• Analytical Mindset: bridge AI theory with real-world robotic deployment.
• Communication & Collaboration: team player, interdisciplinary work, conferences.

Skills

Machine Learning

Deep Learning

Reinforcement Learning

Imitation Learning

Physics-Informed Neural Networks

Python

C++

ROS/ROS2

PyTorch

TensorFlow

JAX

MuJoCo

Gazebo

Isaac Sim

Education

Master’s degree in Robotics, Computer Science, Mechanical/Electrical Engineering, Automation Engineering, Physics or related field

Tools

Python

C++

ROS/ROS2

PyTorch

TensorFlow

JAX

Isaac Sim

MuJoCo

Gazebo

Job description

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:

• 3,750 € salary per month for a full-time
• The possibility of accommodation in the Roche Boarding House or convenient transport connections to Munich with the Roche Shuttle

Start: As of January 2027 or according to the agreement for a period of 3 years.

Do you need further support? Please have a look at our FAQs, you will find them via https://careers.roche.com/global/en/faq.

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.

Roche is an Equal Opportunity Employer. We believe it's urgent to deliver medical solutions right now - even as we develop innovations for the future. We are passionate about transforming patients’ lives. We are courageous in both decision and action. And we believe that good business means a better world. That is why we come to work each day. We commit ourselves to scientific rigor, unassailable ethics, and access to medical innovations for all. We do this today to build a better tomorrow. We are proud of who we are, what we do, and how we do it. We are many, working as one across functions, across companies, and across the world. We are Roche.