Philipp Van Kempen
Research Assistant at Technical University of Munich
Munich, Bavaria, Germany
Summary
👤
Senior🎓
Top SchoolPhilipp Van Kempen is a Research Assistant at the Technical University of Munich with 11 years of hands-on experience at the intersection of mathematics, computer science, and electrical engineering. He brings practical expertise in embedded systems, configuration management, and machine-learning model compilation from roles ranging from internships to academic research and tutoring. As a contributor to the high-profile Apache TVM project, he implemented TFLite integration enhancements, C++ kernel support, and frontend flexibility for custom operator conversions—work that bridges model representation and efficient code generation. His academic foundation (MSc and BSc in Electrical and Computer Engineering from TUM) is matched by applied industry experience at Infineon and multiple engineering internships. Colleagues value his analytical rigor and the uncommon combination of low-level systems fluency with compiler/ML engineering. Based in Munich, he continues to focus on turning mathematical insight into performant, production-ready tooling.
11 years of coding experience
Master of Science - MS, Electrical and Computer Engineering, Master of Science - MS, Electrical and Computer Engineering at Technical University of MunichBachelor of Science (B.S.), Electrical Engineering and Information Technology, 1.7, Bachelor of Science (B.S.), Electrical Engineering and Information Technology, 1.7 at Technische Universität MünchenA-level and Information Technology Assistant, Mathematics, 1.2, A-level and Information Technology Assistant, Mathematics, 1.2 at Berufskolleg Beckum
German, English, Spanish
Github Skills (19)
tvm10
python10
machine-learning10
relayer10
deeplearning-ai10
compiler-compiler10
deep-learning10
compiler10
tflite10
relay10
c-language9
cprogramming-language9
performance-analysis8
tensorflow8
performance-monitor8
Programming languages (16)
Github contributions (5)
apache/tvm
Oct 2021 - Sep 2022
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
Backend Developer & ML Engineer
Backend Developer & ML EngineerContributions:25 reviews, 8 commits, 13 PRs in 11 months
Contributions summary:Philipp contributed to the TFLite integration within the TVM project. They added the functionality to overwrite the OperatorConverter class in the Relay frontend, providing flexibility for custom operator conversions and alternative implementations. The user also fixed inconsistencies in function name handling within the graph executor and added support for C++ kernels and added a new text/relay frontend. The commits demonstrate work related to model compilation, code generation, and potentially optimization for machine-learning models.
metalvulkancompilertensoropencl
PhilippvK/tvm
Jan 2021 - Mar 2025
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Contributions:204 pushes, 137 branches in 4 years 2 months
cpugpu-programmingcudagpu-accelerationtvm
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.