PhD student Digital in-memory brain-inspired edge processors for Edge AI

Tiramisu project (Marie Curie funded)

Digital in-memory brain-inspired edge processors for Edge AI

What you will do

As a researcher of this PhD project you will work on methods, strategies, and architectural enhancements aimed at improving the energy efficiency, latency, scalability and robustness of in-memory and near-memory AI processing and acceleration.

You will have the opportunity to work on exciting software/hardware research exploring neuromorphic computing concepts and ideas such as asynchronous event-based and dataflow processing, quantization and model compression, brain-inspired modelling for algorithm-hardware co-optimization, (dynamic) model mapping, on-device adaptation, and other.

The application scope of interest is edge AI (drones, automotive, IoT) and the solution scope is (but not limited to) multimodal sensor-fusion with spiking and/or quantized neural network models on digital accelerators that benefit from advanced nanoelectronics technologies.

This PhD position is part of the MSCA Doctoral Network “Training and Innovation in Reliable and Efficient Chip Design”, that will give you connect you to leading industry and academic experts, developing industry-relevant solutions.

Your host will be IMEC-Holst (Eindhoven) and will spend time in secondments with industrial and academic partners.
Your PhD-awarding university will be Delft University of technology (TU-Delft). 

What we do for you

By joining imec in Eindhoven, you will be part of a multi-disciplinary team of disruptive innovators and thinkers that build smart solutions by adding AI / Neuromorphic circuits and algorithms in edge devices such as IoT sensors, drones, automotive, biomedical (implantables, wearables, ingestibles), etc. Imec in general is a place for high-TRL innovative, and also foundational research, close to applications, and offering unique access to IC technology.
Through imec-Academy you will have a wide range of training possibilities next to the cross-institutional training enabled by the MSCA Doctoral network of this project.   

Who you are

• You hold a BSc/MSc degree in a field relevant to at least one of ML/AI, computer architectures, neuromorphic computing (e.g. computer science, electrical engineering, computer systems engineering, physics, informatics, other).
• You have good analytical thinking skills and fair programming skills in C/C++ and python, and/or digital design.
• You have had exposure to neural-network training (e.g. using frameworks such as PyTorch, TensorFlow, or other) and/or computer architecture design is a plus.
• You are easy collaborator, have ability to work independently, are motivated to work in an interdisciplinary environment, and eager to expand your knowledge and understanding in the fields of computer architectures and AI.
• You are an excellent communicator in English (written and spoken).
• You have not been working or studying in the Netherlands for more than 12 months in the last 36 months (according to MSCA Doctoral Network rules).  

Interested

Does this position sound like an interesting next step in your career and work on making societal impact? Don’t hesitate to apply today by submitting your full resume, grades, and motivation letter. Do you have any questions about this position? You may contact Manolis Sifalakis at manolis.sifalakis@imec.nl or Kanishkan Vadivel at kanishkan.vadivel@imec.nl.
Have questions about the recruitment process? Martijn Kohl at jobs@imec of the Talent Acquisition Team will be happy to assist you.

IMPORTANT notes:

You will need to apply both here through the imec portal, as well as at the portal of the MSCA Doctoral Network “Training and Innovation in Reliable and Efficient Chip Design for Edge AI (tiramisu-project.eu)”.

Before applying make sure you satisfy the EU eligibility requirements and conditions of the MSCA DN programme:

• Eligibility:      https://tiramisu-project.eu/vacancies/eligibility
• Conditions:   https://tiramisu-project.eu/vacancies/conditions