Doctoral Thesis: Detection and Recovery Mechanisms for Analog Edge AI Hardware (f/m/div)

Infineon Technologies; Deutschland; Vor Ort; EUR 40.000 - 80.000; Vollzeit

Zusammenfassung

Ein innovatives Unternehmen sucht leidenschaftliche Doktoranden für das TIRAMISU-Projekt, das sich mit der Zuverlässigkeit von Edge AI Hardware beschäftigt. In dieser spannenden Rolle entwickeln Sie Mechanismen zur Verbesserung der Hardware-Zuverlässigkeit und führen umfassende Tests unter realen Bedingungen durch. Sie profitieren von einer engen Zusammenarbeit mit einer Partneruniversität und erhalten wertvolle Einblicke in die Industrie. Diese Position bietet eine hervorragende Gelegenheit, Ihre Forschungskompetenzen in einem dynamischen Umfeld zu erweitern und einen bedeutenden Beitrag zur Zukunft der Technologie zu leisten. Wenn Sie eine Leidenschaft für wissenschaftliche Forschung und innovative Lösungen haben, freuen wir uns auf Ihre Bewerbung.

Qualifikationen

• Interesse an komplexen, interdisziplinären Aufgaben.
• Erste Erfahrungen mit Metamodellierung und modellgetriebener Architektur.

Aufgaben

• Entwicklung von Mechanismen zur Verbesserung der Zuverlässigkeit in digitalen Edge AI Plattformen.
• Evaluierung von Hardware-Gesundheit durch Fehleranalyse und Monitoring-Techniken.

Kenntnisse

Wissenschaftliche Forschung

Präsentationsfähigkeiten

Objektorientierte Programmierung (C++, Python)

Eingebettete Programmierung (C, Assembler)

Digitales Design und RTL-Modellierung (VHDL, Verilog)

Metamodellierung

Modellgetriebene Architektur

Ausbildung

Masterabschluss in Computer Engineering

Masterabschluss in Elektrotechnik

Jobbeschreibung

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. We are looking for two PhD candidates within the "TIRAMISU" project (Training and Innovation in Reliable and Efficient Chip Design for Edge AI), which will be funded by the Marie Skłodowska-Curie Actions (MSCA) Doctoral Networks/Industrial Doctorates (DN-ID) in 2023, as part of the European Union's EU Framework Programme for Research and Innovation Horizon Europe. The scope of this thesis are faults in digital Edge AI Hardware especially their measurement, their analytical determination and the comparison of the results of both. The goal of this thesis is to adjust the analytical determination of fault probabilities for future valuations. To get there, several versions of a hardened RISC-V SoC with closely or loosely coupled Edge AI accelerator and incorporating fault localization and reporting mechanisms shall be designed, FPGA prototyped, and implemented. An analytical analysis shall be performed with industry standard methods. Further an experiment shall be performed by of running the implemented chip under a particle stream and measuring the faults. The thesis will be written in cooperation with Taltech University and under the supervision of professor Maksim Jenihhin.

Job description:

The tasks within the thesis will consist of:

1. Development of low/zero overhead mechanisms that can be integrated in digital edge AI platforms in order to improve the overall reliability and safety.
2. Investigation of dedicated mechanisms to facilitate the evaluation and the assessment of hardware health, e.g., the number of occurred bit-flips or wrong computation results.
3. Exploration of in-field, run-time monitoring techniques of hardware health, and mechanisms to collect error measurements by using functional communication units, e.g. on-chip busses for system evaluations.
4. Development of schemes to ensure reliability by design and by activating in-field mechanisms which ensure the intended functionality or recover the hardware.
5. Implementation of mechanisms to stress the hardware or to emulate a relevant stress to enable a thorough verification of the various assessment methods for the hardware health.
6. Evaluation of these solutions on real chips and under stress of atomic particles.

Your Profile:

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.

As the ideal candidate you:

• Have not been working or studying in Germany for more than 12 months in the last 36 months.
• Are eligible for full-time PhD studies and have a master's degree in Computer Engineering, Electrical Engineering or a related field with very good grades.
• Are interested in complex, interdisciplinary and interlinked tasks and should like to solve them together with colleagues.
• Possess good presentation skills, helping you to present challenging issues clearly and simply.
• Gained first experience with metamodeling, (template-based) code generation and/or model-driven architecture.
• Have knowledge in object-oriented programming with languages such as C++ and Python and embedded programming with C and/or Assembler.
• Possess good knowledge of digital design and RTL modeling in VHDL and/or (System)Verilog and embedded system architectures.
• Are interested in generation and recursive application of generation, e.g. generation of generators.
• Possess very good language skills in English and ideally German.

Please attach the following documents to your application:

• CV in English
• Cover Letter
• Latest grades transcript from university

Why Us:

#WeAreIn for driving decarbonization and digitalization.

As a global leader in semiconductor solutions in power systems and IoT, Infineon enables game-changing solutions for green and efficient energy, clean and safe mobility, as well as smart and secure IoT. Together, we drive innovation and customer success, while caring for our people and empowering them to reach ambitious goals. Be a part of making life easier, safer and greener.

Are you in?

The central R&D organization "Design Enabling and Services" (DES) provides the design environments (design-systems) to the different product development teams at Infineon. With leading edge design methods, complex building blocks and a wide range of product development services DES enables Infineon's advanced IC development. This means the complete value creation chain from abstract system models down to the fully verified product layout which ensures high quality manufacturing readiness.

We are on a journey to create the best Infineon for everyone.This means we embrace diversity and inclusion and welcome everyone for who they are. At Infineon, we offer a working environment characterized by trust, openness, respect and tolerance and are committed to give all applicants and employees equal opportunities. We base our recruiting decisions on the applicant's experience and skills.

We look forward to receiving your resume, even if you do not entirely meet all the requirements of the job posting. Please let your recruiter know if they need to pay special attention to something in order to enable your participation in the interview process.

Click here for more information about Diversity & Inclusion at Infineon.