PhD scholarship in Embedded AI

Are you interested in conducting cutting edge research in the intersection of the Internet of Things (IoT) and Artificial Intelligence (AI) focusing on resource-limited edge IoT devices? Are you a hands-on person, interested in low-level programming, applied machine learning, and deploying IoT devices in the real world? The Embedded Systems Engineering (ESE) section of DTU Compute offers in collaboration with Grundfos, a PhD scholarship funded by the Digital Research Centre Denmark (DIREC) https://direc.dk/. The position is available from June 1, 2022, or later according to mutual agreement.

Artificial Intelligence (AI) has become a pervasive technology to design systems having the ability to function in a smart way such as self-adaptivity and on-the-fly performance optimization following the operation conditions. But today many of the solutions under development requires AI execution in the cloud or on a larger computer platform with an operating- and file-system available. To enable execution on end-devices (sensors, pumps etc.) or at the edge, an AI translation is needed to allow execution on these resource constrained devices. In essence, this will enable AI to perceive and learn in real-time by mirroring critical AI functions across multiple disparate systems, platforms, sensors, and devices operating at the edge. A great challenge here is an 'easy to use' toolchain to support the translation to an efficient embedded AI (eAI).

Grundfos is currently investigating toolchains but also foresee a need for further development of these tools and methods to master the complexity of various AI architectures as well as the optimization of these. Also safe, secure, and easy deployment of embedded AI updates in systems already in service needs to be developed.

Some relevant cases you could demonstrate your work on in Grundfos could be on developing ML algorithms to predict health status on pumps based on vibration data or creating ML models that optimizes the pump usage to lower energy consumption or make ML models that optimize systems (buildings or factories) where pumps are part of the infrastructure. What these problems all have in common are the use of data to continuously improve performance and your focus will be on how Grundfos can increase the speed of taking ML ideas from prototypes in e.g., python to deployment on an embedded device.

Responsibilities
This PhD project is focused on developing novel eAI algorithms and systems to monitor, deploy, and optimize end-device performance in IoT deployments in real-time. To that end, the project will investigate and propose novel real-time AI-based algorithms and toolchains. Pump-based systems from Grundfos will be used as case-studies for acquiring knowledge of industrial systems and as platforms for demonstrating achieved solutions.

Some tentative tasks within the project include:

• Analyse state of the art for tools/tool chains for embedded AI development.
• Investigate state of the art Neural Networks as well as other machine learning model types such as tree ensemble models with easier interpretation, easier tuning, and more robustness towards incomplete data.
• Investigate highly scalable microcontroller platforms all the way from very tiny devices with few kilo bytes of memory and limited calculation performance for deeply embedded AI inference in dedicated end-node applications and up to hugely capable microprocessor devices incorporating AI accelerators for edge type applications with local or federated learning abilities
• Investigate how to enable easy eAI deployment in coexistence with other existing and unchanged embedded software tasks running on the same target device.
• Deployment and monitoring of the developed models and tools in an industrial setting of smart pumps at Grundfos.

Qualifications
You must have a two-year master's degree (120 ECTS points) or a similar degree with an academic level equivalent to a two-year master's degree. Applicants with a 300 ECTS (i.e., 5 years) education at bachelor and master level are also encouraged to apply.

You must have a master's degree in computer science or computer engineering or equivalent. You must have a strong background in applied machine learning and low-level systems programming in C. Knowledge of microcontroller programming is desirable. Some experience with FPGA design is also desirable. Experience in writing and publishing scientific papers is an advantage. You must be fluent in English, both speaking and writing, and possess excellent communication skills.

Approval and Enrolment
The scholarship for the PhD degree is subject to academic approval, and the candidate will be enrolled in one of the general degree programmes at DTU. For information about our enrolment requirements and the general planning of the PhD study programme, please see DTU's rules for the PhD education. https://www.dtu.dk/english/Education/PhD/Rules

Assessment
The assessment of the applicants will be made by Professor Jan Madsen, DTU Compute and Head of Electronics, Director Technology Innovation, Thorkild Kvisgaard, Grundfos.

We offer
DTU is a leading technical university globally recognized for the excellence of its research, education, innovation, and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility. Although you will be employed at DTU, you are expected to spend considerable time at Grundfos in Bjerringbro, Jutland.

Salary and appointment terms
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The period of employment is 3 years.

You can read more about career paths at DTU here: http://www.dtu.dk/english/about/job-and-career/working-at-dtu/career-paths

Further information
Further information may be obtained from Professor Jan Madsen ([email protected]).

You can read more about DTU Compute at www.compute.dtu.dk/english. You can read more about the ESE section of DTU Compute at https://www.compute.dtu.dk/english/research/research-sections/ese. You can read more about DIREC at https://direc.dk/. You can read more about Grundfos at https://www.grundfos.com.

If you are applying from abroad, you may find useful information on working in Denmark and at DTU at DTU - Moving to Denmark. https://www.dtu.dk/english/about/job-and-career/moving-to-denmark

Application procedure
Your complete online application must be submitted no later than 29 April 2022 (Danish time). Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply online", fill out the online application form, and attach all your materials in English in one PDF file. The file must include:

• A letter motivating the application (cover letter)
• Curriculum vitae
• Grade transcripts and BSc/MSc diploma (in English) including official description of grading scale

You may apply prior to ob­tai­ning your master's degree but cannot begin before having received it.

All interested candidates irrespective of age, gender, race, disability, religion, or ethnic background are encouraged to apply.

DTU Compute
DTU Compute is a unique and internationally recognized academic department with 385 employees and 11 research sections spanning the science disciplines mathematics, statistics, computer science, and engineering. We conduct research, teaching and innovation of high international standard - producing new knowledge and technology-based solutions to societal challenges. We have a long-term involvement in applied and interdisciplinary research, big data and data science, artificial intelligence (AI), internet of things (IoT), smart and secure societies, smart manufacturing, and life science. At DTU Compute we believe in a diverse workplace with a flexible work-life balance.

Technology for people
DTU develops technology for people. With our international elite research and study programmes, we are helping to create a better world and to solve the global challenges formulated in the UN's 17 Sustainable Development Goals. Hans Christian Ørsted founded DTU in 1829 with a clear vision to develop and create value using science and engineering to benefit society. That vision lives on today. DTU has 12,900 students and 6,000 employees. We work in an international atmosphere and have an inclusive, evolving, and informal working environment. DTU has campuses in all parts of Denmark and in Greenland, and we collaborate with the best universities around the world.

Kilde: Jobnet.dk