Vacancy No. 3658

Research associate / PhD candidate (f/m/d) on the topic In- and Near-Memory-Computing Architectures for Machine Learning

Since many years, the Chair for Embedded Systems works internationally successfully in the areas of computer engineering, such as embedded system architecture. Many interesting and open problems in these areas need to be addressed to successfully deploy such systems in modern application domains. As an example, the most urgent questions about in- and near-memory computing architectures are highlighted in the following.

Job description

Future mobile networks will become more and more self-managed at the base station level, due to the need for complex but real-time decision making. Machine learning algorithms will enable this transition since they outperform classical approaches in many areas. However, the base station hardware has to be adapted to this increasing workload. Using common computer architectures will be insufficient. They will struggle to provide the performance under the given energy constraints because they separate memory and computing resources creating substantial overhead through data transfers. The near-memory-computing (NMC) paradigm tries to minimize such transfers. The in-memory-computing (INC) concept is even more embedded and places computations directly inside the memory. In the scope of this research project, possible computer architectures shall be investigated. But at which level in the memory hierarchy do changes have the biggest effect? Depending on the analysis, different research questions have to be answered. Coherence between caches and main memory has to be maintained if data is being processed directly in the main memory and not moved through the caches. This also raises the challenge to handle concurrent accesses on the same data. Additionally, the NMC and INC architectures should be as flexible as possible, e.g., by using the memory for compute and storage at the same time or by running user-provided code on small CPU cores inside the main memory. With direct access to the whole memory, this raises questions for the virtual memory management and has severe security implications. The above mentioned problems and many more have to be tackled to enable future technologies by reducing energy consumption and improving performance.

Personal qualification

You should have a very good Master's degree (or equivalent) in CS or EE with background or specialization in the above-mentioned topics. The ideal candidate (f/m/d) shows a strong interest and motivation to deepen in these topics to a level required for a doctorate. Knowledge of computer architecture, programming skills in C/C++, or scripting languages like Python will be required. Fluency in written and spoken English is a prerequisite. We are looking for a highly motivated candidate (f/m/d) with a strong commitment to research ethics and teamwork. Good communicative skills are mandatory due to the interdisciplinary structure of the project and the team. Your application should include a cover letter and an up-to-date CV.


Salary category E13, depending on the fulfillment of professional and personal requirements.

Organizational unit

Institute for Computer Engineering (ITEC)

Starting date

Contract duration

limited to four years with the possibility to obtain a Ph.D.

Application up to


Contact person in line-management

For technical information, please contact Prof. Henkel, 0721/608-46050; topic Application SWC_NMLA.


Please apply online using the button below for this vacancy number 3658 .
Personnel Support is provided by 

Ms Brückner
phone: +49 721 608-42016,

Kaiserstr. 12, 76131 Karlsruhe

We prefer to balance the number of employees (f/m/d). Therefore we kindly ask female applicants to apply for this job.

If qualified, severely disabled persons will be preferred.