Ph.D. Student for AI for Chip Design (m/f/d, full time E13)

19.07.2023, Wissenschaftliches Personal

We are an active and lively research group which is passionate about science. We are working in an environment which may best be characterized by the passion to accomplish something new—complemented by teamwork and fostering personal relationships. From assistants, students, researchers, postdocs to professors; we are all working hand in hand, are highly committed, and engaged with our work. We know how to celebrate our successes, but also how to get through setbacks together!

In the next months, we are going to extend our research group at the Technical University of Munich (www.cda.cit.tum.de). Accordingly, we are currently searching for a Ph.D. student to join our team on AI for Chip Design!

Our Research

In our group, we create, modify, and adapt AI methods (such as Machine Learning, Metric Learning, Reinforcement Learning, Graph Representation Learning, Generative Models, Domain Adaptation, etc.) for Design Automation applications. To this end, we focus on developing general methods and, then, apply them on fields where their performance overcomes the state of the art. In an upcoming project together with an industrial partner, we aim to establish these methods within a practical relevant environment. In the future, we are aiming to extend our activities and are looking for candidates with (one or more of) of the following expertise:

• Use of generative AI in the chip design process
• Optimization and Reinforcement Learning methods for problems of design/layout
• Exploration of Heuristics and Data-driven Methods for the generation of design blocks
• Automated Test and Verification of designs created using Machine Learning methods
• Utilization of feedback loops to improve design choices
• Creation of an automated pipeline and frameworks for data generation and storage
• Innovation in the Machine Learning algorithms for EDA in terms of Computational Complexity, Performance Scores, etc.

To learn more about our previous work, please check out our website (www.cda.cit.tum.de/research/machine_learning/).

Your Profile

We are looking for a Ph.D. student who is willing to learn and explore new topics while playing nice in a team. Your main task will be the development, conceptualization, and eventual implementation of new machine learning and optimization methods in design automation for Chip Design. Our focus on interdisciplinary partnerships and networks will enable you to meet many interesting people (at places all over the world) and present your work at top-notch conferences and journals in our domain.

You should have completed your Master/Diploma studies with top grades in Computer Science, Artificial Intelligence, Mathematics, Electrical Engineering, or a similar subject. Most importantly, you should be creative, passionate about research, driven by curiosity, and be able to think outside-of-the-box. You will need strong coding skills (preferably Python, but also other software and hardware description languages) as well as experience with Machine Learning Frameworks (such as TensorFlow, PyTorch, Stable Baselines). Solid knowledge in the areas of machine learning, algorithmics, mathematical optimization, as well as experience with analog/digital design is of advantage.

Join our Team

While we are obviously interested in your CV and background (if applicable, please also add your list of publications, projects, cooperations, etc. as well as your GitHub profile). Most importantly however, tell us what motivates you to join our team and work on AI for chip design. Let us know why you would be a great candidate! We are looking forward to hearing from you! Please send your application (in English or German) to Prof. Dr. Robert Wille (robert.wille@tum.de) until 19.08.2023.

Severely disabled applicants will be given preference if they are essentially of the same suitability and qualifications. The Technical University of Munich aims to increase the proportion of women, so applications from women are expressly welcomed.

Kontakt: robert.wille@tum.de