Summary
Max Fruehauf is a lead compiler engineer based in Munich with a decade of experience building production-grade ML compilers and AI accelerator software. At Tensordyne he scaled a custom compiler and microcode stack to run LLM, diffusion, and speech workloads on proprietary AI ASICs, owning validation, simulator execution, and correctness testing. He blends robotics and computer vision research—publishing CVPR-highlighted work on topology extraction—with deep IR and compiler expertise, having evaluated OpenXLA and MLIR to steer architecture decisions. Max is also a hands-on mentor who onboarded cross-team engineers and translated research prototypes into deployable toolchains. His background spans robotics, systems control, and 3D graphics, giving him a rare multidisciplinary perspective on geometry, compilers, and ML systems. Less obvious: he combines hardware-aware code generation with a researcher's eye for high-fidelity geometry, which helps optimize models for both accuracy and accelerator throughput.
10 years of coding experience
1 year of employment as a software developer
Bachelor's, Informatics, Bachelor's, Informatics at Technical University of Munich
Master's degree, Robotics, Systems and Control, 5.89 / 6.0 passed with distinction, Master's degree, Robotics, Systems and Control, 5.89 / 6.0 passed with distinction at ETH Zürich
Exchange Semester, Computer Science, Exchange Semester, Computer Science at National University of Singapore
German, English, Chinese, French