Master Thesis

Summary

Join Bosch and contribute to the future of AI acceleration! As a thesis intern, you will work with an international team to explore hardware-based optimization for neural network deployment. Your responsibilities include conducting literature research on state-of-the-art optimization strategies, evaluating existing work, investigating and optimizing NN deployment methods, implementing solutions in the torch framework, and documenting results. This 6-month internship requires a Master's degree in a relevant field, strong Python/C++ skills, experience with neural network compilers (like TVM), and deep learning knowledge. The position offers flexible work arrangements, allowing you to work remotely from your home in Germany or at the Bosch location in Renningen.

Requirements

• Master studies in the field of Electrical Engineering, Computer Science or comparable
• Strong experience in Python/C++
• Experience with neural network compiler (TVM)
• Basic hardware knowledge
• Deep Learning Concepts
• Linux
• LaTeX
• Excel at working independently
• Organize tasks effectively
• Stay highly motivated to achieve your goals
• Good English
• Enrollment at university

Responsibilities

• Conduct literature research on state-of-the-art NN deployment optimization strategies
• Evaluate related work in terms of its suitability for an overarching interaction between efficient HW/SW codesign
• Investigate, evaluate, and optimize NN deployment methods and compiler tool stack particularly focusing on graph optimizations and strategies such as e.g. operation fusion or reordering
• Implement your solution in our torch framework and evaluate it in extensive simulations
• Document and discuss the results

Preferred Qualifications

• Work flexibly from your home in Germany
• Work at the Bosch location in Renningen

Benefits

• Mobile working within Germany
• Remote work possible