PhD Performance optimization for network- and data processing in 6G networks

Ghent University – imec IDLab Research group

IDLab is a research group of Ghent University, as well as a core research group of imec.  IDLab performs fundamental and applied research on data science and internet technology and counts over 300 researchers.  IDLab is also part of imec, the world-leading research and innovation hub in nano-electronics and digital technologies. The combination of our widely acclaimed leadership in microchip technology and profound software and ICT expertise is what makes us unique.

The IDLab NetModel team where this vacancy is offered consists of engineers and scientists who are building models for the future Internet. NetModel investigates network control mechanisms, network optimization and performance-related aspects of networks. The group has a strong track record in the domains of optical networks, network performance optimization, and software-defined networking.
Context
The next generation of (mobile) communication networks introduces tremendous potential for new data-driven applications such as auto-guided vehicles, AR/VR devices, smart clothing, cooperative robots in industry, or using drones for inspecting critical infrastructure. 

Many of these new services require extremely efficient networking and data processing at the edge of the network, even in very small devices close to the data sources or users. This has introduced all kinds of programmable hard- and software acceleration platforms to improve pure network packet processing such as DPDK, VPP, netfpga, SmartNICs, etc., but also to accelerate the processing of the data itself using GPUs, NPUs, FPGAs to accelerate machine learning. 

Network control architectures as a result need to evolve to meet at once performance and sustainability goals, and therefore they need to be extended supporting higher dynamicity and versatility, providing programmability upon all these new types of devices and components. Depending on the instantaneous service demand, novel hardware needs to be optimally allocated and configured to accommodate those services who need them most. 

We are hiring highly motivated researchers with an analytical mind, and good system engineering skills to assess and model the performance gains obtainable by exciting new hardware devices, and to think outside the box to design profiling and orchestration systems which can optimally use these devices in the context of futuristic data-driven network services.

What you will do

• Under the supervision of professors in the team, you will prepare a PhD dissertation over a duration of about 4 years (coupled to a positive evaluation after the first year).
• You evaluate and model performance of novel network- and data processing technologies
• You develop control and orchestration network algorithms to optimally use novel network- and data processing technologies
• You publish and present results both at international conferences and in scientific journals.
• You implement proof of concepts of designed mechanisms in experimental proof of concepts
• You validate your research through adequate quantitative measurements in a statistically meaningful manner
• You tightly collaborate with IDLab colleagues within the NetModel team, as well as in other teams where appropriate.
• You will participate in the framework of national and European funded research projects and collaborate with research partners from industry.
• You will assist the research group with limited educational tasks.

Who you are

• Holder of a Master degree in Engineering, preferably Computer Science or Electrical Engineering, or Master in Informatics.
• Strong affinity with (Linux-based) operating systems and network engineering techniques
• Deep interest in acceleration technologies (e.g,. GPUs, NPUs, SmartNICs)
• You are thrilled by performance modelling and tweaking.
• Good (system-level) programming skills and ability to adapt to particular language or environment (C/C++, Rust, Python, …)
• Strong mathematical and analytical skills
• Comfortable with cloud technologies (Docker, Kubernetes, VMs, etc.) or quickly able to learn these
• You like to deep-dive into research problems and have an experimental mindset
• You value security- and privacy-related aspects of data and associated technology 
• You work independently, have a strong feeling of responsibility and can commit to timing and milestones set forward by different research projects.
• You are a team player and have strong communication skills.
• A good knowledge of English (oral and written) is a must. Any knowledge of Dutch (oral) is a plus.

Interested?

Apply by sending an email to prof. Wouter Tavernier (mailto: Wouter.Tavernier@UGent.be) and prof. Didier Colle (mailto: Didier.Colle@UGent.be).

Your application should include:

• your resume (curriculum vitae)
• motivation letter (indicating both your research background/interest and any specific research skills)
• a copy of your diploma and diploma supplement (with overview of all courses followed).

Applications without resume, letter or transcripts will not be considered.