Master Thesis - Language-Conditioned Traffic Scene Generation with Multimodal Inputs - REF73286W

Company Description

Continental develops pioneering technologies and services for sustainable and connected mobility of people and their goods. Founded in 1871, the technology company offers safe, efficient, intelligent and affordable solutions for vehicles, machines, traffic and transportation. In 2023, Continental generated sales of 41.4 billion and currently employs around 200,000 people in 56 countries and markets.

Job Description

Hey, you are looking for an exciting thesis and would like to gain valuable insights into the field of Language-Conditioned Traffic Scene Generation? Then we have just the thing for you!

We are looking for you starting in February for a period of 6 months to support us in our AI laboratory in Berlin. We will need you mostly on site in Berlin. But we also understand that there are days when you'd rather work from home. Therefore, together we find a solution that suits us all - remote working hours are therefore possible in consultation with your supervisor.

The project explores novel approaches to generating realistic traffic scenarios using large language models and multimodal inputs for autonomous driving applications. Building upon recent advances like CTG, LCTGen and TrafficGEN, you will investigate methods to enhance scenario generation with improved spatial consistency and semantic control.

This position offers a unique opportunity to conduct publishable research at the intersection of natural language processing, computer vision, and autonomous driving. The results of this work are intended for submission to conferences in the field.

The following tasks are to be processed in this Master's thesis:

• Develop and implement novel algorithms for language-conditioned traffic scene generation using multimodal inputs
• Investigate methods for ensuring physical consistency and realism in generated scenarios
• Design and conduct experiments to evaluate the performance and effectiveness of the proposed methods
• Collaborate with team members to integrate language processing and computer vision techniques
• Contribute to the preparation of research papers for publication in academic journals or conferences for master thesis

While not mandatory, this position is particularly well-suited for students who are considering a future in research or pursuing a PhD. We are open to explore alternative way to achieve the end goal of thesis.

Qualifications

Are you wondering whether you are suitable for the thesis in the field of Detecting and Eliminating Adversarial Attacks? Here are key qualifications we are looking for:

• You study in the field of Artifical Intelligence, Computer, Science, Robotics or comparable courses of study, so that you have basic aspects of our area of responsibility
• Strong foundation in deep learning, particularly transformer architectures and LLMs as wells as proficiency programming experience in Python and PyTorch with demonstrable project experience are absolutely necessary in the context of this position
• You should also have an understanding of computer vision fundamentals and modern architectures
• It would be great if you have experience with multimodal data processing and contributions to open-source projects, a keen interest in autonomous driving and traffic simulation as well as experience with research methodology and scientific writing
• We expect as well the ability to analyze complex data and generate insightful visualizations
• Fluent English language skills in word and writing are absolutely necessary for us

In addition to these technical requirements, we are also looking for certain properties and skills:

• You are independent, goal-oriented and structured and know how to work effectively without losing track - always pay attention to high-quality results
• Analytical thinking and problem-solving kills are also beneficial and can help you solve the tasks effectively
• Creativity and flexibility are a matter of course for you and help you to find unconventional solutions
• A very good communication and teamwork skills are particularly important for us - after all, we always have to work together on solutions

Before you submit your application, there are a few things you should think about: We need your current immatriculation certificate and your current grade level as well as an excerpt from the study regulations regarding the completion of a thesis in order to be able to process your application.

If you are not from the EU area, please also send us your valid residence permit and your work permit including the additional sheet.

Applications from severely handicapped people are welcome.

Additional Information

• You will receive qualified support from our experienced specialists and PhDs to improve your professional knowledge and practical skills
• Your commitment to us is fairly remunerated: We know that your work is valuable and want to ensure that you are adequately remunerated
• We offer you flexible working hours with hybrid working models, where you have the opportunity to occasionally work from home, because we know how important the interaction of private and professional life is.
• Our location is centrally located in Berlin and we look forward to welcoming you to our Co-Working Space AI Campus
• We provide a powerful GPU infrastructure, because only with excellent technology can we achieve great
• Participate in journal clubs and networking events and share technical topics with your colleagues on campus

If you find yourself in our position and feel like working with us on exciting projects, then apply now and become part of our team!

Diversity, Inclusion & Belonging are important to us and make our company strong and successful. We offer equal opportunities to everyone - regardless of age, gender, nationality, cultural background, disability, religion, ideology or sexual orientation.

Ready to drive with Continental? Take the first step and fill in the online application.