Scientist XAI for Large Language Models

Future. Discover. Together.

The "Explainable Artificial Intelligence" (XAI) group focuses on the development of powerful methods, and the analysis of aspects of interpretability and explainability in machine learning. A core research of the group is the intersection of explainability, fairness and robustness of machine learning models. Become a part of our team and join us on our journey of research and innovation!

What you will do

• Your task will be the development, publication, practical application, theoretical analysis and evaluation of the next generation of XAI algorithms in novel model architectures and expert domains

• The scientific work offers the possibility of a doctorate

What you bring to the table

•  An excellent degree (Master of Science or equivalent) in Machine Learning, Physics, Mathematics or a related field

• A solid background in theoretical foundations of deep learning, statistics, optimization

• A strong understanding of and practical experience with Deep Neural Networks

• A firm grasp of Large Language Models (LLMs)

• Extensive experience and profound expertise of recent XAI explanation methods and current XAI research topics such as LRP/CRP

• A strong research potential and experience in machine learning (research internships, e.g. first author publications)

• Experience in training and evaluation of machine learning models on large high performance computing infrastructure

• A firm grasp of the latest frameworks, back-ends and programming languages relevant for Deep Learning, especially Python 3 and PyTorch

• Excellent programming skills and experience with Open Source software development

• Familiarity with collaborative tools such as Git

• Experience in the domain of Ethics and fairness in AI

• The ability to work independently, as well as in a team, in a structured manner

• Excellent knowledge of the English language in spoken and written form

• High levels of skill and motivation for shaping a more transparent future of AI

• 100% on-site availability to promote creative collaboration among peers 

What you can expect

• The ability to work on exciting and highly relevant research topics in the domain of XAI

• A highly motivated, international team and an excellent hardware and compute infrastructure

• Collaborations with international machine learning experts, and the participation in activities of these groups in international conferences, such as NeurIPS, CVPR, ICML, etc.

• The opportunity to contribute to cutting-edge XAI research in high-profile research projects

• Fascinating challenges in a scientific and entrepreneurial setting

• Attractive salary package according to TvöD with 30 vacation days, pension scheme (VBL), wealth creation benefits (VWL)

• Modern and excellently equipped workspace in a central location

• Great and cooperative working atmosphere in an international team

• Flexible working hours 

• Support if you wish to do a doctorate

• Opportunities to work from home

• Extensive training-, health- and sports offers

• Various employee discounts and discounted BVG ticket

• Offers for families (parent-child office, emergency care, leisure activities, etc.)

The position is initially limited to 2 years. An extension is explicitly desired.

The weekly working time is 39 hours. This position is also available on a part-time basis. We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Appointment, remuneration and social security benefits based on the public-sector collective wage agreement (TVöD). Additionally Fraunhofer may grant performance-based variable remuneration components.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future. 

Interested? Apply online now. We look forward to getting to know you!
 

Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute HHI 

www.hhi.fraunhofer.de 

Requisition Number: 76090                Application Deadline: 10/19/2024