Postdoctoral position in Machine-Learning in Safety-Critical Cyber-Physical Systems - Befattningen är under tillsättning eller redan tillsatt, och det är inte längre möjligt att lämna in en ansökan

The Department of Applied Physics and Electronics at Umeå University has an immediate opening for a postdoctoral position for the project Machine-Learning in Safety-Critical Cyber-Physical Systems. The position is full-time for two years with start date August 01, 2021, or as agreed. Application deadline is April 9, 2021.

Umeå University, Faculty of Science and Technology
Umeå University is dedicated to providing creative environments for learning and work. We offer a wide variety of courses and programmes, world leading research, and excellent innovation and collaboration opportunities. More than 4 100 employees and 34 000 students have already chosen Umeå University. We welcome your application!

Department of Applied Physics and Electronics
The Department of Applied Physics and Electronics currently has around 90 employees and conducts research in fields such as Energy Engineering, Laser Spectroscopy, Biomedical Engineering and Electronics and System Engineering. For more information, see www.tfe.umu.se/forskning.

Project description and working tasks
The project focuses on the inter-disciplinary area of real-time embedded and Cyber-Physical Systems (CPS), which feature tight integration and closed-loop interactions between embedded, networked processors and their surrounding physical environment. Our overall objective is to develop techniques for addressing the challenges in the design and analysis of safety-critical CPS to make them safer and more efficient.

Machine Learning (ML) components are increasingly adopted in today’s safety-critical CPS such as intelligent and autonomous vehicles. It is challenging to achieve high levels of safety certification (e.g., ISO 26262 for automotive E/E systems) for such systems due to complexity and unpredictability of ML algorithms, especially Deep Neural Networks (DNNs). This project aims to develop rigorous techniques for safety assurance of ML-enabled CPS. Research topics include: design-time assurance with reachability analysis; runtime assurance with the Simplex architecture; Out-of-Distribution detection for vision-based perception; real-time scheduling/resource management of ML components on resource-constrained embedded systems. The working tasks mainly consists of theoretical derivations and experimental studies in simulation environments (as opposed to field experiments). The concrete working tasks will be defined taking into consideration of the candidate’s research background and interests, as long as they are within project scope and can potentially generate high-quality publications.

Qualifications
A person who has been awarded a doctorate or a foreign qualification deemed to be the equivalent of a doctorate in Electrical Engineering or Computer Science qualifies as a postdoctoral fellow. Priority should be given to candidates who have completed their doctoral degree no more than three years before the closing date of the application. A candidate who has completed their degree prior to this may be considered if special circumstances exist. Special circumstances include absence due to illness, parental leave or clinical practice, appointments of trust in trade unions or similar circumstances.

The applicant should have a strong background in Machine Learning, especially Deep Learning and Reinforcement Learning. Very good skills in written and oral English are required as is good ability to act both individually as in a team. Creativity and ability to take initiatives are also required.

Knowledge of real-time systems and safety-critical/autonomous systems is meritorious. 

Application
A complete application includes:

• Personal letter with maximum of 2 pages,
• Curriculum vitae CV with publication list,
• Certified copy of doctoral degree certificate,
• Certified copy of doctoral thesis,
• Contact information for at least two reference persons,
• Other documents that you wish to claim.

The application, including attached documents, must be written in English or Swedish. The application is made through our electronic recruitment system. Documents sent electronically must be in Word or PDF format. Log in to the system and apply via the button at the end of this page. The closing date is April 9, 2021. (“Certified” means that a person (who can be identified) can guarantee the authenticity of the certificate.)

Further details are provided by Zonghua Gu (zonghua.gu@umu.se) and Thomas Olofsson (head of department) (thomas.olofsson@umu.se)