Doctoral Thesis: Machine Learning in Functional Verification for Security Applications (f/m/div)*

  • Infineon Technologies
  • Dresden, Germany
  • 23/08/2021
Full time Data Science Data Engineering Machine Learning Data Analytics Big Data Data Management Statistics

Job Description

The industrial doctorate at Infineon: Pursue a doctoral degree at a university and gain professional experience simultaneously - an ideal start for your career. Advance your research with us and profit from our vast network of doctoral candidates and the expertise of a university. Mentorship is handled by both professors and dedicated Infineon employees. Functional verification represents one of the main tasks in today’s hardware design cycles. The later bugs are found during this process, the more expensive remedying them can be. Therefore, it is essential to have a comprehensive verification approach right from the beginning. In order to measure its progress, functional coverage has become a widely used technique for this task. However, reaching coverage closure mainly depends on the manner in which stimulus is defined or generated. For this reason, considerable effort has been spent on finding solutions to automate and speed up the covering procedure in general.In order to shorten the turn-around times during development, recent advancements in machine learning and artificial intelligence shall be applied to achieve better results with a shorter amount of time and less effort. The main focus of the work will be on security-critical IPs like hardware monitors which keep track of the design integrity during real time. The thesis will be written in cooperation with TU Kaiserslautern and under the supervision of Prof. Dr.-Ing. Wolfgang Kunz.
The tasks within the thesis will consist of:

  • Research on machine learning approaches in functional verification
  • Optimized stimulus generation through the support of machine learning for closing functional coverage
  • Development and application of machine learning approaches for detecting trojans in malicious hardware monitors
  • Functional analyses for detecting hardware trojans in 3rd party IPs

A doctoral student is a research enthusiast,
› …whose interests are scientific research combined with the passion for Infineon’s innovative products and applications.
› …who enjoys working in an industrial environment in combination with an Infineon partner university.
› …who appreciates open communication and the contribution of an international environment.
› …and is thus an excellent candidate for a further academic or industrial career after completion of their thesis.

You are best equipped for this task if you have:

  • A university master’s degree in Electrical Engineering, Computer Science or similar with excellent results
  • High interest in innovation , research and scientific writing
  • Strong analytical and problem solving skills
  • Willingness to tutor bachelor and/or master students
  • Excellent English language skills as a must, fluency in German as an advantage

Know-how in following topics is preferable - but not mandatory …

  • Experience with Verification Methodologies (UVM), Assertions (SystemVerilog Assertions) and C/C++
  • Ideally already gained experience with formal tools
  • Excellent programming skills (preferably Python, C++)

This is the world’s first high-volume production site for power semiconductors on 300 mm wafers