Working Student in Spiking and Convolutional Neural Network Training with Hardware-Aware

Developing innovative technology solutions and bringing them to application - that is our goal at the Fraunhofer Institute for Photonic Microsystems IPMS. With our expertise in the development of photonic microsystems, related technologies including nanoelectronics and wireless communication solutions, we create - in flexible and interdisciplinary teams - technologies for innovative products in a wide range of markets such as automotive, industrial and aerospace.

At the Center for Nanoelectronic Technologies (CNT) of Fraunhofer IPMS, we develop advanced AI systems through the integration of Convolutional Neural Networks (CNNs) and Spiking Neural Networks (SNNs), with a strong emphasis on deploying these models on hardware-constrained  edge platforms. The position focuses on developing robust, efficient, and hardware-aware neural network models. A solid understanding of SNNs, their training dynamics, and their relevance for neuromorphic and low-power systems is essential. In addition, candidates should demonstrate strong experience in optimizing neural networks through quantization, error modeling, and co-training techniques that consider real-world hardware imperfections.

What you will do

• Develop and train CNN and SNN models utilizing frameworks such as Keras, PyTorch, and SNNtorch
• Implement GPU acceleration through CUDA to enable efficient neural network training
• Apply hardware-aware design concepts including quantization, error modeling, and mixed-precision training
• Develop and evaluate co-training methods to enhance model resilience against hardware non-idealities and failures
• Analyze model performance under hardware constraints, evaluating trade-offs between efficiency and accuracy
• Collaborate with interdisciplinary teams to adapt and optimize neural network architectures for specific hardware implementations
• Document the research methodology, experimental outcomes, and best practices for dissemination within the team and wider academic community

What you bring to the table

• Completed Bachelor's degree and ongoing Master's or Diploma studies in Electrical Engineering, Computer Science, Artificial Intelligence, or a related discipline
• Strong understanding and hands-on experience with Spiking Neural Networks (SNNs) is a core requirement; familiarity with Convolutional Neural Networks (CNNs) is also expected
• Proven experience with Python frameworks such as Keras, PyTorch, or SNNtorch for neural network development
• Practical experience with GPU acceleration using CUDA
• Proven experience with hardware-aware techniques, including quantization, error resilience strategies, and mixed-precision training, is expected
• Strong ability to independently master new technical fields and complex scientific concepts
• Excellent written and verbal communication skills in English to operate effectively in an international research environment
• (Optional) Understanding of digital and analog electronic basics

What you can expect

We offer you an exciting task and valuable insights into the methods and procedures of a modern high-tech research institute. A motivated and dynamic team awaits you in a very well-equipped research and development environment. In addition, we offer you connecting points within the framework of your studies or your career entry, e.g. a topic for your thesis or the beginning of your career at Fraunhofer IPMS. We support you!

The weekly working time is a maximum of 20 hours and is to be coordinated flexibly. The position is initially limited for 1 year. A long-term collaboration is strived. We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Remuneration according to the general works agreement for employing assistant staff.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future. 

Interested? Apply online now. We look forward to getting to know you!

Contact

Mr Eric Graebe
Human Resources
Phone: +49 351 8823 1505
 

Mr. Alptekin Vardar
Specialty Department
Phone: +49 351 2607 3201

Fraunhofer Institute for Photonic Microsystems IPMS

www.ipms.fraunhofer.de 

Requisition Number: 77874