Initial situation:

Deep learning (DL) systems play a crucial role in the processing and analysis of large volumes of data. In industrial image processing (IIP), this relates to the processing of component images using convolutional neural networks (CNN) in order to detect any defects. A central problem in processing is load balancing, i.e. the even distribution of the workload across the available resources. Load balancing is a challenge in DL evaluations due to the dynamic nature of workloads in production and the complexity of DL models. The development of innovative approaches that enable efficient, dynamic load balancing is therefore of great importance in order to further increase the performance and efficiency of DL systems.

Tasks:

• Literature research: Research on existing methods and technologies of load balancing, especially in the context of deep learning evaluations.
• Analysis: Listing of the current challenges and limitations of existing load balancing approaches in DL evaluations.
• Concept development: Creation of a concept for load balancing that is specifically tailored to the requirements and special features of DL evaluations.
• Implementation: Implementation of a prototype of the developed load balancing concept. The implementation should be carried out in a common programming language or framework for DL evaluations (preferably PyTorch).
• Evaluation: Carrying out an evaluation of the prototype. This includes measuring the performance improvements in terms of efficiency in various production scenarios.

Your Profile:

• Ongoing education in a HTL
• Motivation & reliability

Our offer:

• Payment of printing costs for very good or good results
• Support from a supervisor from the relevant specialist department
• Get to know Fill as a potential employer and contribute your own ideas and knowledge
• Exciting opportunity to supplement your theoretical knowledge with practical experience
• Very good working atmosphere in an award-winning family business

Time period:

Start from now

We look forward to receiving your application!