Postdoctoral Researcher on Advanced Circuit Design for Analog in-memory Computing for AI
What you will do
In recent years, artificial intelligence (AI) capabilities have vastly improved, leading to AI utilization in an ever-increasing number of applications and devices. Some of the most powerful AI algorithms, called deep learning algorithms or deep neural networks, require considerable amounts of computation, memory and energy during both training and inference. This complexity has kickstarted a quest for computationally- and energy-efficient deep-learning accelerators or chips. One potential solution to mitigate the challenges related to deep learning algorithms, is to perform the billions of computations in the memory itself. Compared to classical Von Neumann architectures, in which computations are performed on a central processor after memory elements have been fetched from outside, compute-in-memory approaches have the promise to increase energy efficiency by orders of magnitudes, while at the same time allowing for the required high throughput.
Based on its technological know-how and capabilities, Imec is developing analog compute-in-memory (ACiM) solutions for deep learning algorithms. In ACiM circuits, deep learning computations are performed in the analog domain and in the memory by employing standard or more exotic memory devices. Although very promising on paper, there are still many circuit design challenges to be resolved to enable and optimize ACiM for real-word applications.
This post-doc leverages Imec's knowledge of novel memory and logic technology, 3D integration technology and algorithms to address this overall challenge. More specifically:
- You will develop innovative circuits for analog compute-in-memory (ACiM) solutions.
- This work includes both circuit design in advanced CMOS technologies and the exploration of possibilities of and requirements for novel (memory or logic) devices.
- You will keep an eye on new algorithms, and future developments such as Spiking Neural Networks.
- You will be part of a dedicated machine learning team with expertise at the algorithm, architecture, circuit and device level.
- During this work, you will acquire experience in a wide range of technological domains and work on tomorrow’s technology and leverage it for next generations of AI hardware
- You will help drive imec’s technology and architecture roadmap to build the semiconductor technology for AI Hardware Architectures of the near and far away future.
What we do for you
We offer you the opportunity to join one of the world’s premier research centers in nanotechnology at its headquarters in Leuven, Belgium. We offer you an exciting position in a rapidly growing, multi-disciplinary team and the chance to define the AI Architectures of the near and far away future.
We are proud of our open, multicultural, and informal working environment with ample possibilities to take initiative and show responsibility. We commit to supporting and guiding you in this process; not only with words but also with tangible actions. Through imec.academy, 'our corporate university', we actively invest in your development to further your technical and personal growth.
We are aware that your valuable contribution makes imec a top player in its field. Your energy and commitment are therefore appreciated by means of a competitive salary.
Who you are
- You have a PhD in the field of Computer Engineering or Electrical Engineering.
- You have experience in analog circuit design
- Specific experience in mixed-signal design and memory periphery design is a strong plus
- You can work with novel technology and are creative in working with experimental PDKs and technology stacks
- You have at the very least some basic knowledge about neural networks and are willing to take a deep dive
- We value experience with
- Computer architecture and/or digital design
- Algorithm mapping on hardware
- DAC and ADC design
- You work in a structured, transparent and accurate way.
- You are a constructive team player and actively share experience and knowledge with colleagues.
- Your networking skills, creativity, persistence and passion for what you do are highly valued.
- We are looking for your excellent communication skills in English, as you will work in a multicultural team and closely with our partners.
This postdoctoral position is funded by imec through KU Leuven. Because of the specific financing statute which targets international mobility for postdocs, only candidates who did not stay or work/study in Belgium for more than 24 months in the past 3 years can be considered for the position (short stays such as holiday, participation in conferences, etc. are not taken into account).