Master Thesis

Roofline is building a software development kit to run any model on disruptive hardware at the edge. We are looking for talented and ambitious engineers that are passionate about technology to design and implement new components in our software stack. You will work alongside other world class engineers to enable the full spectrum of AI applications across heterogeneous hardware platforms.

• Design and implement new components of our next generation compiler built upon MLIR
• Iterate with customers to design the best compiler technology and the best user experience possible
• Partner with a growing open-source community to foster a strong ecosystem around Roofline
• The following thesis topics are currently available, please highlight your preferred topic/area in your application:
  • MLIR Interpreter
  • Optimizing performance with vector instructions for RISC-V
  • Blockbuster (new tiling strategy)

• Enrolled student at a European top-level university. (We have relationships to RWTH (Aachen), LMU (Munich) and EPFL (CH), which eases the path to finding a supervisor for students from these unis).
• Enrolled in a Master's program in Computer Science/ Electrical Engineering or a related field
• Knowledge and hands-on experience in C++ and Python
• Proven understanding of software engineering principles, data structures, design patterns, and algorithms
• Desire to work with a growing community of open-source contributors
• Ambition and curiosity to solve complex problems, a strong mindset to take ownership of your tasks to drive our solutions forwards, and collaborative attitude to foster our culture

• Experience working with MLIR or LLVM.
• Knowledge of AI algorithms, experience with using AI accelerators or compiling to relevant hardware
• Knowledge of data motion networks, data flow programming models, and optimized AI libraries
• Knowledge about hardware architectures for CPUs, GPUs, or NPUs/accelerators is a plus