Summary
The Mod4Comp research unit is inviting applications for a PhD position focused on performance and energy modeling for spiking neural networks. This role involves developing models to enhance the efficiency of future AI technologies by optimizing computational processes.
PhD Position in Performance and Energy Modeling for Spiking Network Simulations, Germany
Designation
PhD Position – Performance and Energy Modeling for Spiking Network Simulations
Research Area
- Neuromorphic Computing
- Computational Neuroscience
- Performance and Energy Modeling
Location
Aachen, Germany
Eligibility/Qualification
| Criteria | Details |
|---|---|
| Educational Background | Master’s degree in Computer Science, Mathematics, Physics or a related field |
| Knowledge | Neuromorphic Computing or Computational Neuroscience is a plus |
| Programming Skills | Experience with C++, MPI, OpenMP; knowledge of CUDA is a plus |
| Language Proficiency | Very good command of written and spoken English (B2 level CEFR); German is a plus |
| Additional Skills | Analytical and creative thinking; excellent communication skills; team-oriented |
Description
As a doctoral researcher under Dr. Susanne Kunkel, you will contribute to the advancement of simulation technology for large-scale spiking neural networks. Your tasks will include:
- Working with the NEST simulation code and experimental branches.
- Analyzing the spiking network simulation cycle.
- Developing proxy applications for different processing stages.
- Benchmarking simulations on various computing systems.
- Collaborating with national and international partners and contributing to publications.
How to Apply
Interested candidates should submit their applications via the online application portal. Applications sent via email will not be accepted. For detailed information on the application process, refer to the FAQs available on the employment page.
Last Date to Apply
Open Until the position is filled. Early applications are encouraged.
Explore this opportunity to shape the future of energy-efficient computing in the exciting field of neuromorphic systems!
