3 dagen geleden - Radboud Universiteit (RU) - Nijmegen
PhD Position: Trustworthy Edge AI
Want to be part of exciting EU H2020 project to tackle the challenges of black-box AI and data management towards EU top agenda on Trustworthy AI? Check this out.
- Mekelweg, Delft, Zuid-Holland
- Tijdelijk contract / Tijdelijke opdracht
- Uren per week:
- 36 - 40 uur
- € 2395 - € 3061 per maand
This PhD project is part of a major EU H2020 project on trustworthy AI. The offered PhD position is to explore trustworthy AI and develop an explanatory platform that accounts AI systems based on its quantified quality.
Currently, AI schemes applied in security solutions focus mainly on accuracy and performance (e.g., precision, recall, resource utilization) but lack effective accountability from explainable and transparent perspectives. Existing solutions mainly rely on empirical methods (i.e. on the observation of responses to sampled test data) for evaluating system performance, with limited underlying formal methods or guidelines to support the validity of the system behaviours, especially in terms of legal and ethical obligations. Given such challenge, you will investigate explainability features to quantify the different properties of an AI system, such that it is possible to account its overall execution pipeline. In the context of IoT edge and 5G security and privacy domain, you will develop a dedicated platform and a set of metrics to evaluate if the explanations make sense to the end-users or developers of the existing intelligent systems.
During the PhD, the candidate will conduct this research with the project consortium and prepare scientific articles presenting the research at conferences and in journals. To enable the candidate to do this successfully, TU Delft offers personal and professional training courses in the form of a graduate school, in which the candidate will participate (the fee is paid by the project and there are no additional costs for this). Furthermore, in addition to her/his scientific supervisors, the applicant will receive an independent senior research as mentor, to aid her personal career development.
The candidate must have a master's degree in computer science, information science, engineering, or a similar degree with an academic level equivalent to the master's degree in engineering. Excellent academic records in analytical, mathematical and programming (Python/Java/C++) are preferred. Good command of spoken and written English is required. Development experience with AI, IoT systems is a plus.
The position is part of H2020 project and entails the following tasks: 1) Investigate and derive explainability features to quantify the different properties of an AI system, such that it is possible to account its overall execution pipeline; 2) Develop a dedicated platform and a set of metrics to evaluate if the explanations make sense to the end-users or developers of the existing intelligent systems in collaboration with academic and industrial partners; 3) Support and contribute to project coordination; 4) Contribute to teaching activities at ESS department.
As part of H2020 project consortium, you will have the opportunity to conduct practical research in cooperation with world leading industrial companies through the consortium network.
TU Delft offers PhD-candidates a 4-year contract, with an official go/no go progress assessment after one year. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2395 per month in the first year to € 3061 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.
The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.
For more information about this vacancy, please contact Dr. Aaron Ding, Assistant Professor, email: firstname.lastname@example.org, tel: + 31152785659.
For more information about the selection procedure, please contact Olivie Beek, HR Advisor, email: email@example.com.