NExTWORKx PhD position Safe Use of AI in Telecommunication Networks

NExTWORKx*is the strategic partnership between the Telecom and ICT service provider KPN and Delft University of Technology. NExTWORKx aims to develop new concepts & technology in telecommunication and artificial intelligence, to respond to new disruptive technologies and to continue the development of talent. NExTWORKx enters its second research phase with a focus on developing and applying concepts from network science to model the huge number of real-time interactions between software components and data sets and to enable monitoring and control. AI-based algorithms will be developed for monitoring information flows and smart contracts. A trusted layer for monitoring and control is crucial for every network and digital infrastructure individually, but also across critical infrastructures, data sharing and smart city platforms. NExTWORKx announces the hiring of 4 PhD students who will be mentored by both TUDelft and KPN staff. The 4 PhD projects contribute to the above goals, but each with a different focus:

1. Safe use of AI in telecommunication networks
2. Resilient cross domain networks for critical infrastructure
3. Secure data sharing in federated edge clouds
4. Co-evolution of telecommunication networks and urban systems

Safe use of AI in telecommunication networks: Telecommunication networks are becoming highly programmable and automated. Network Functions (NFs) in software, for example for routing and access management, can be deployed by generic hardware. As a result of this virtualization, the supplier landscape for (software based) NFs becomes more diverse (lower barrier for entry) and innovative (software development cycle rather than hardware renewal). Challenge for telecommunication network operators is to both source innovative and cost-effective NFs and to integrate these NFs from multiple vendors into a secure and reliable overall network architecture. This challenge is also referred to as “Operating Disintegrated Networks (ODIN)”.
Both individual NFs and the overall network management software will include AI based algorithms and will change in real time. Hence, classical software and integration testing will not necessarily ensure the correct functioning of the overall telecommunication network.
Research challenges include:

• How to model the interaction between the different software components (NFs, automated network management), including the interplay with the underlying (virtualised) physical infrastructure
• How to model the impact of AI (closed loop learning) on the potential “action spaces” of the different software components and the resulting potential network behaviour
• Develop concepts of observability and controllability for AI based NFs and automating telecom network management.
• Develop design guidelines for AI based NFs and automating telecom network management to guarantee network safety and security and to be able to explain (backtrack) in case of failure (explainable AI)

*KPN and Delft University of Technology will work together on new ICT technologies (overons.kpn)

Requirements:

We are looking for brilliant PhD candidates with a strong interest to the join a university-company collaboration on future Networking. The ideal candidate is multidisciplinary, well-versed in telecommunications (protocols, architectures, design and performance), algorithms, probability theory, data science and network science.
Because of project definitions, we are looking for EU citizens.
Doing a PhD at TU Delft requires English proficiency at a certain level to ensure that the candidate is able to communicate and interact well, participate in English-taught Doctoral Education courses, and write scientific articles and a final thesis. For more details please check the Graduate Schools Admission Requirements.

Salary Benefits:

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1,5 year contract with an official go/no go progress assessment within 15 months. Followed by an additional contract for the remaining 2,5 years assuming everything goes well and performance requirements are met.
Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2872 per month in the first year to € 3670 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 a monthly work costs contribution. Flexible work schedules can be arranged.
For international applicants, TU Delft has the Coming to Delft Service. This service provides information for new international employees to help you prepare the relocation and to settle in the Netherlands. The Coming to Delft Service offers a Dual Career Programme for partners and they organise events to expand your (social) network.

36 - 40 hours per week

Mekelweg 2