Master-Thesis “World Models for Physical AI”

AIT Austrian Institute of Technology GmbH

Center for Vision, Automation & Control

The AIT Austrian Institute of Technology is Austria’s largest Research and Technology Organisation. The Center for Vision, Automation & Control located in Vienna invites applications for a master thesis. Within the Competence Unit Assistive & Autonomous Systems, the team researches and develops technology components for assistance systems and the automation of commercial vehicles and unmanned aerial platforms.

As part of this master's thesis, you will investigate how world models can be brought to field robotics using real-world-scale LiDAR, image, and sensor data. The goal is to enable physical AI for large-scale machinery, such as cranes, by designing efficient world model architecture that runs on on-device hardware.

Your tasks

Dive into the literature on world model architectures for physical AI, including reconstruction-based approaches, JEPA-style latent prediction, and self-supervised representation learning on LiDAR and multi-sensor data.
Implement and compare encoder designs for LiDAR and image data, such as voxel-based, point-based, bird's-eye-view, or tokenized representations.
Design and train world models that capture how scenes evolve over time.
Define suitable metrics and evaluate predictive quality and robustness under challenging conditions.
Explore compatibility with edge and on-device hardware.
Analyze and present findings and potentially contribute to a publication at a leading robotics or machine learning venue.

Your qualifications

Ongoing master’s studies in Artificial Intelligence, Computer Science, Robotics, or a comparable technical field.
Strong programming skills, especially in Python and PyTorch, along with a solid understanding of deep learning.
Experience with 3D data or point cloud processing, computer vision, or generative models is a plus.
Enjoyment of application-oriented challenges in industrial contexts.
High level of commitment and team spirit.
Excellent English skills, both written and spoken; German skills are a plus.

What to expect

Duration: 6 months, flexible start, ideally as soon as possible.
Location: Vienna, hybrid.
Intensive mentorship by experienced AIT scientists and experts.
Opportunity to publish results in peer-reviewed conferences and collaborate with leading industry partners.
EUR 1,027.40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.

Please submit your complete application documents online, consisting of CV, cover letter, relevant certificates, transcript of records, and proof of identity.

Bewerben

.js-only-skeleton { display: none !important; }

Center for Vision, Automation & Control

Your tasks

Dive into the literature on world model architectures for physical AI, including reconstruction-based approaches, JEPA-style latent prediction, and self-supervised representation learning on LiDAR and multi-sensor data.
Implement and compare encoder designs for LiDAR and image data, such as voxel-based, point-based, bird's-eye-view, or tokenized representations.
Design and train world models that capture how scenes evolve over time.
Define suitable metrics and evaluate predictive quality and robustness under challenging conditions.
Explore compatibility with edge and on-device hardware.
Analyze and present findings and potentially contribute to a publication at a leading robotics or machine learning venue.

Your qualifications

Ongoing master’s studies in Artificial Intelligence, Computer Science, Robotics, or a comparable technical field.
Strong programming skills, especially in Python and PyTorch, along with a solid understanding of deep learning.
Experience with 3D data or point cloud processing, computer vision, or generative models is a plus.
Enjoyment of application-oriented challenges in industrial contexts.
High level of commitment and team spirit.
Excellent English skills, both written and spoken; German skills are a plus.

What to expect

Duration: 6 months, flexible start, ideally as soon as possible.
Location: Vienna, hybrid.
Intensive mentorship by experienced AIT scientists and experts.
Opportunity to publish results in peer-reviewed conferences and collaborate with leading industry partners.
EUR 1,027.40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.

Please submit your complete application documents online, consisting of CV, cover letter, relevant certificates, transcript of records, and proof of identity.

Hauptstandort

Random Phone Number
randomemail@example.com

Ansprechpartner

.js-only-skeleton { display: none !important; }

Center for Vision, Automation & Control

Your tasks

Dive into the literature on world model architectures for physical AI, including reconstruction-based approaches, JEPA-style latent prediction, and self-supervised representation learning on LiDAR and multi-sensor data.
Implement and compare encoder designs for LiDAR and image data, such as voxel-based, point-based, bird's-eye-view, or tokenized representations.
Design and train world models that capture how scenes evolve over time.
Define suitable metrics and evaluate predictive quality and robustness under challenging conditions.
Explore compatibility with edge and on-device hardware.
Analyze and present findings and potentially contribute to a publication at a leading robotics or machine learning venue.

Your qualifications

Ongoing master’s studies in Artificial Intelligence, Computer Science, Robotics, or a comparable technical field.
Strong programming skills, especially in Python and PyTorch, along with a solid understanding of deep learning.
Experience with 3D data or point cloud processing, computer vision, or generative models is a plus.
Enjoyment of application-oriented challenges in industrial contexts.
High level of commitment and team spirit.
Excellent English skills, both written and spoken; German skills are a plus.

What to expect

Duration: 6 months, flexible start, ideally as soon as possible.
Location: Vienna, hybrid.
Intensive mentorship by experienced AIT scientists and experts.
Opportunity to publish results in peer-reviewed conferences and collaborate with leading industry partners.
EUR 1,027.40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.

Please submit your complete application documents online, consisting of CV, cover letter, relevant certificates, transcript of records, and proof of identity.

Hauptstandort

Random Phone Number
randomemail@example.com

Ansprechpartner

.js-only-skeleton { display: none !important; }

Center for Vision, Automation & Control

Your tasks

Dive into the literature on world model architectures for physical AI, including reconstruction-based approaches, JEPA-style latent prediction, and self-supervised representation learning on LiDAR and multi-sensor data.
Implement and compare encoder designs for LiDAR and image data, such as voxel-based, point-based, bird's-eye-view, or tokenized representations.
Design and train world models that capture how scenes evolve over time.
Define suitable metrics and evaluate predictive quality and robustness under challenging conditions.
Explore compatibility with edge and on-device hardware.
Analyze and present findings and potentially contribute to a publication at a leading robotics or machine learning venue.

Your qualifications

Ongoing master’s studies in Artificial Intelligence, Computer Science, Robotics, or a comparable technical field.
Strong programming skills, especially in Python and PyTorch, along with a solid understanding of deep learning.
Experience with 3D data or point cloud processing, computer vision, or generative models is a plus.
Enjoyment of application-oriented challenges in industrial contexts.
High level of commitment and team spirit.
Excellent English skills, both written and spoken; German skills are a plus.

What to expect

Duration: 6 months, flexible start, ideally as soon as possible.
Location: Vienna, hybrid.
Intensive mentorship by experienced AIT scientists and experts.
Opportunity to publish results in peer-reviewed conferences and collaborate with leading industry partners.
EUR 1,027.40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.

Please submit your complete application documents online, consisting of CV, cover letter, relevant certificates, transcript of records, and proof of identity.

Hauptstandort

Random Phone Number
randomemail@example.com

Ansprechpartner

Master-Thesis “World Models for Physical AI”

AIT Austrian Institute of Technology GmbH

Center for Vision, Automation & Control

Your tasks

Dive into the literature on world model architectures for physical AI, including reconstruction-based approaches, JEPA-style latent prediction, and self-supervised representation learning on LiDAR and multi-sensor data.
Implement and compare encoder designs for LiDAR and image data, such as voxel-based, point-based, bird's-eye-view, or tokenized representations.
Design and train world models that capture how scenes evolve over time.
Define suitable metrics and evaluate predictive quality and robustness under challenging conditions.
Explore compatibility with edge and on-device hardware.
Analyze and present findings and potentially contribute to a publication at a leading robotics or machine learning venue.

Your qualifications

Ongoing master’s studies in Artificial Intelligence, Computer Science, Robotics, or a comparable technical field.
Strong programming skills, especially in Python and PyTorch, along with a solid understanding of deep learning.
Experience with 3D data or point cloud processing, computer vision, or generative models is a plus.
Enjoyment of application-oriented challenges in industrial contexts.
High level of commitment and team spirit.
Excellent English skills, both written and spoken; German skills are a plus.

What to expect

Duration: 6 months, flexible start, ideally as soon as possible.
Location: Vienna, hybrid.
Intensive mentorship by experienced AIT scientists and experts.
Opportunity to publish results in peer-reviewed conferences and collaborate with leading industry partners.
EUR 1,027.40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.

Please submit your complete application documents online, consisting of CV, cover letter, relevant certificates, transcript of records, and proof of identity.

Bewerben

.js-only-skeleton { display: none !important; }

Center for Vision, Automation & Control

Your tasks

Dive into the literature on world model architectures for physical AI, including reconstruction-based approaches, JEPA-style latent prediction, and self-supervised representation learning on LiDAR and multi-sensor data.
Implement and compare encoder designs for LiDAR and image data, such as voxel-based, point-based, bird's-eye-view, or tokenized representations.
Design and train world models that capture how scenes evolve over time.
Define suitable metrics and evaluate predictive quality and robustness under challenging conditions.
Explore compatibility with edge and on-device hardware.
Analyze and present findings and potentially contribute to a publication at a leading robotics or machine learning venue.

Your qualifications

Ongoing master’s studies in Artificial Intelligence, Computer Science, Robotics, or a comparable technical field.
Strong programming skills, especially in Python and PyTorch, along with a solid understanding of deep learning.
Experience with 3D data or point cloud processing, computer vision, or generative models is a plus.
Enjoyment of application-oriented challenges in industrial contexts.
High level of commitment and team spirit.
Excellent English skills, both written and spoken; German skills are a plus.

What to expect

Duration: 6 months, flexible start, ideally as soon as possible.
Location: Vienna, hybrid.
Intensive mentorship by experienced AIT scientists and experts.
Opportunity to publish results in peer-reviewed conferences and collaborate with leading industry partners.
EUR 1,027.40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.

Please submit your complete application documents online, consisting of CV, cover letter, relevant certificates, transcript of records, and proof of identity.

Hauptstandort

Random Phone Number
randomemail@example.com

Ansprechpartner

.js-only-skeleton { display: none !important; }

Center for Vision, Automation & Control

Your tasks

Dive into the literature on world model architectures for physical AI, including reconstruction-based approaches, JEPA-style latent prediction, and self-supervised representation learning on LiDAR and multi-sensor data.
Implement and compare encoder designs for LiDAR and image data, such as voxel-based, point-based, bird's-eye-view, or tokenized representations.
Design and train world models that capture how scenes evolve over time.
Define suitable metrics and evaluate predictive quality and robustness under challenging conditions.
Explore compatibility with edge and on-device hardware.
Analyze and present findings and potentially contribute to a publication at a leading robotics or machine learning venue.

Your qualifications

Ongoing master’s studies in Artificial Intelligence, Computer Science, Robotics, or a comparable technical field.
Strong programming skills, especially in Python and PyTorch, along with a solid understanding of deep learning.
Experience with 3D data or point cloud processing, computer vision, or generative models is a plus.
Enjoyment of application-oriented challenges in industrial contexts.
High level of commitment and team spirit.
Excellent English skills, both written and spoken; German skills are a plus.

What to expect

Duration: 6 months, flexible start, ideally as soon as possible.
Location: Vienna, hybrid.
Intensive mentorship by experienced AIT scientists and experts.
Opportunity to publish results in peer-reviewed conferences and collaborate with leading industry partners.
EUR 1,027.40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.

Please submit your complete application documents online, consisting of CV, cover letter, relevant certificates, transcript of records, and proof of identity.

Hauptstandort

Random Phone Number
randomemail@example.com

Ansprechpartner

.js-only-skeleton { display: none !important; }

Center for Vision, Automation & Control

Your tasks

Dive into the literature on world model architectures for physical AI, including reconstruction-based approaches, JEPA-style latent prediction, and self-supervised representation learning on LiDAR and multi-sensor data.
Implement and compare encoder designs for LiDAR and image data, such as voxel-based, point-based, bird's-eye-view, or tokenized representations.
Design and train world models that capture how scenes evolve over time.
Define suitable metrics and evaluate predictive quality and robustness under challenging conditions.
Explore compatibility with edge and on-device hardware.
Analyze and present findings and potentially contribute to a publication at a leading robotics or machine learning venue.

Your qualifications

Ongoing master’s studies in Artificial Intelligence, Computer Science, Robotics, or a comparable technical field.
Strong programming skills, especially in Python and PyTorch, along with a solid understanding of deep learning.
Experience with 3D data or point cloud processing, computer vision, or generative models is a plus.
Enjoyment of application-oriented challenges in industrial contexts.
High level of commitment and team spirit.
Excellent English skills, both written and spoken; German skills are a plus.

What to expect

Duration: 6 months, flexible start, ideally as soon as possible.
Location: Vienna, hybrid.
Intensive mentorship by experienced AIT scientists and experts.
Opportunity to publish results in peer-reviewed conferences and collaborate with leading industry partners.
EUR 1,027.40 gross per month for 20 hours/week based on the collective agreement, plus additional company benefits.

Please submit your complete application documents online, consisting of CV, cover letter, relevant certificates, transcript of records, and proof of identity.

Hauptstandort

Random Phone Number
randomemail@example.com