close

PhD position on Neuro-symobolic AI for microfabricated fluidic sensors

Research / Academic
Enschede

The Pervasive Systems research group at the University of Twente is looking for a PhD candidate to perform research and development on a multidisciplinary project involving Neuro-symobolic AI and microfabricated fluidic sensors.

The main research objectives are:

  • Conduct research in neuro-symbolic AI for microfabricated fluidic sensors, including but not limited to designing and implementing lightweight but accurate algorithms and models, conducting experiments, analyzing data, and interpreting results.
  • Collaborate with the team to develop and optimize microfabrication processes for the sensors.
  • Develop and test new sensor designs and configurations, and evaluate their performance.
  • Write technical reports and research papers for publication in top-tier journals and conferences (Percom, Ubicomp, IJCAI, AAAI, NIPS, ICML).


The prospective candidates are expected to perform high-quality and internationally visible research that gets published at top-tier conferences and journals. Candidates will work at the Pervasive Systems Research group, Department of Computer Science, Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) at the University of Twente in the Netherlands. The candidates are expected to collaborate with project partners including the Integrated Devices and Systems (IDS) group, Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), at the University of Twente in the Netherlands.

The project
While a new generation of integrated sensor systems has been developed fast last years, it is now a necessity to explore recent work in symbolic Artificial Intelligence (AI) to overcome these limitations and allow for real-time fluid data processing by using a combination of deep neural networks and physics in flow sensing. By embedding human knowledge of physical quantities into deep neural networks, AI would be able to learn quicker and better how to use the sensing structures on the chip to give a physically relevant output signal. Using deep symbolic AI on microfluidic sensor data is therefore expected to cause a breakthrough in the easy design and use of cutting-edge multiparameter sensing systems. Therefore, the goal of this project is the realization of a demonstrator system containing multiple sensing structures together with a trained neural network, which outperforms the state-of-the-art multiparameter systems, for real-time quality control of products made in chemical or pharmaceutical micro reactors, or in the food industry. Sub-goals include the generation of novel deep symbolic AI that can combine traditional physics rules with modern deep learning techniques to effectively deal with raw sensor data, verify physical constraints, understand the complex physical effects in microfabricated fluid channels, and improve future chip designs based on existing and novel (hidden) causal relations found through AI model interpretability.

The vacancies are within the scope of the MOSAIC - enhancement of MicrOfluidic Sensing with Artificial IntelligenCe project, and is a collaboration between famous research groups of University of Twente and industrial companies. The project is funded by the national research foundation NWO, together with supporting partners from the industry.

Requirements:

  • The ideal candidate has a Master’s degree in either Computer Science, Electronic Engineering, Telecommunication Engineering, or Mathematics.
  • You have experience in relevant areas such as signal processing, symbolic reasoning, embedded systems, data analysis, machine learning and deep learning.
  • Familiarity with microfabrication techniques and fluidic sensing is desirable.
  • Candidates should be interested in solving analytical tasks and developing prototypes, combined with intermediate programming skills (e.g. in R, Python or C-something)
  • Prior experience in generative models, neuro-symbolic AI, causal learning, and efficient deep learning for embedded devices is a plus (with frameworks such as TensorFlow and Keras).
  • Moreover, we are looking for a strong personality to defend your research ideas not only at the university but also in an industrial context.
  • You have good communication skills and you have a strong interest in operating at the crossroads of different disciplines
  • You have an excellent command of English (C1; above IELTS 7 or equivalent)
  • You can able to do independent research and have publication skills

Salary Benefits:

As a PhD candidate, you will be enrolled in the University of Twente. Your work location is Enschede.

  • Fulltime funded position of 4 years
  • We provide excellent mentorship and a stimulating research environment with excellent facilities;
  • You are offered a professional and personal development program within the Twente Graduate School;
  • A starting PhD salary of € 2.872 gross per month in the first year and a salary of € 3.670 in the fourth and last year;
  • A holiday allowance of 8% of the gross annual salary and a year-end bonus of 8.3%;
  • A solid pension scheme;
  • Minimum of 29 holidays per year in case of full-time employment.
Work Hours:

40 hours per week

Address:

Drienerlolaan 5