Master Thesis Student (m/f/d) - Physical AI with Vision Language Action (VLA) Models in Robotics

DENSO; Eching am Ammersee; On-site; EUR 11,000 - 18,000; Full time

Benefits offered by this job

Home office

Health days

Urban Sports Club

Modern offices

Free parking

Open culture

Team events

Job summary

DENSO is seeking a Master Thesis Student (m/f/d) in Physical AI with Vision Language Action (VLA) Models in Robotics. The project centers on evaluating how a physical AI VLA model can generate robust long-horizon actions in unstructured environments.

You will survey state-of-the-art VLA models, implement variants, and set up simulations to benchmark performance. The role offers home office options and a modern, collaborative work environment.

Qualifications

• Currently enrolled in a Computer Science / Engineering Master studies with a focus on data analysis, automotive, engineering or similar.
• Basic understanding of and strong interest in robotics.
• Basic understanding of computer vision.
• Ability to understand and run modern deep-learning and robotics codebases.
• Proficiency in Python or C/C++.

Responsibilities

• Survey state-of-the-art VLA models and world-model approaches.
• Implement and benchmark physical variants using a VLA framework.
• Develop simulation-based setups for model evaluation in challenging scenarios.
• Explore and validate improved integration strategies based on the findings (if feasible).
• Identify and design task-specific fine-tuning strategies to improve model performance (if feasible).

Skills

Robotics basics

Computer vision basics

Deep learning codebases

Education

Master student in Computer Science/Engineering

Tools

Python

C/C++

Job description

Master Thesis Student (m/f/d) - Physical AI with Vision Language Action (VLA) Models in Robotics

Full-time

As an automotive supplier, DENSO is leading in developing and providing components and systems for heating, air conditioning, motor cooling, exhaust gas aftertreatment, automotive electrics and electronics and instrumentation.

Modern Vision Language Action (VLA)models perform well on short-horizon robotic tasks but often struggle with long-term planning and multi-step control. A promising direction is to enhance VLA architectures by integrating them with Physical AI models capable of understanding physical effects, e.g. for challenging, unstructured environments.

For such VLA-based physical AI systems, the project aims to evaluate and quantify a robot’s action-generation capability of a physical AI VLA model for more challenging, unstructured environments, and to develop a clearer understanding how these contribute to more stable and capable long-horizon action generation.

Research Areas

• Survey state-of-the-art VLA models and world-model approaches;
• Implement and benchmark physical variants using a VLA framework;
• Develop simulation-based setups for model evaluation in challenging scenarios;
• Explore and validate improved integration strategies based on the findings (if feasible);
• Identify and design task-specific fine-tuning strategies to improve model performance (if feasible).

Qualifications and Requirements

• Currently enrolled in a Computer Science / Engineering Master studies with a focus on data analysis, automotive, engineering or similar
• Basic understanding of and strong interest in robotics
• Basic understanding of computer vision
• Ability to understand and run modern deep-learning and robotics codebases
• Proficiency in Python or C/C++
• Experience with physical AI, world models, and simulation is a plus

Benefits

• Home office: Possibility to work from home
• Health: Yearly health & wellbeing days, Urban Sports Club membership
• Attractive working environment: Modern offices, canteen onsite and free parking
• Open company culture: Diverse, multicultural team
• Events:Regular company & team events