"PostDoc on Analog CIM-based AI Accelerator Design"

Job Description

Various emerging device technologies and computing paradigms are being investigated for energy-efficient artificial intelligence (AI) applications. Some examples are RRAM or STT-MRAM collectively known as memristor-based Computation-in-Memory (CIM) accelerators. However, these new technologies and computing paradigms face various design challenges in terms of design and technology challenges, application mapping and reliability and non-ideality issues. Thus, there is a growing demand for efficient and reliable memristor CIM-based neuromorphic system design which includes techniques such as reliability-aware mapping and optimization techniques as well as high-quality, and cost-effective mitigation schemes that can guarantee efficient and reliable memristor-based CIM operation for AI workloads.

The Computer Engineering (CE) section of the Quantum & Computer Engineering (QCE) department is looking for a highly motivated PostDoc candidate who wants to work on efficient and reliable analog CIM-based AI accelerator design for future neuromorphic accelerators. The candidate will work on the following:

• Designing efficient analog CIM architecture using emerging memristive devices
• Develop system architecture for analog CIM accelerator
• Develop efficient mapping schemes of AI workloads
• Identifying the non-ideality issues of analog CIM architectures.
• Developing solutions to address the non-ideality issues.

The PostDoc position is part of the SNS (self-healing Neuromorphic Systems), a multi-partner national project involving several key academic and industrial partners such as, Technology University of Eindhoven (TUE), CWI, IMEC and Delft University of Technology.

You will be part of a diverse and passionate research team of academic staff, PhD candidates and Postdoctoral researchers in the Computer Engineering group. Curious to learn more about the project, and perhaps our group? Feel free to browse our webpages: About the SNS project. About our department. About our group.

Job Requirements

For this position, an ideal candidate should have:

• Completed a relevant PhD degree in Electrical Engineering, Computer Engineering, or any other related field relevant to the research;
• Good understanding of analog circuit design;
• Basic understanding of defects, faults, and test solutions for electronic systems is a plus;
• Basic understanding of AI and its hardware implementations is a plus;
• An affinity with teaching and guiding students;
• The ability to work in a team and take initiatives.