Michel Breyer
Principal Engineer at Helbling Technik
Zurich, Zurich, Switzerland
Summary
👤
Senior🎓
Top SchoolMichel Breyer is a Principal Engineer based in Zurich with 11 years of experience at the intersection of AI, machine learning, numerical simulation and robotics. He holds advanced degrees from ETH Zürich including a Doctor of Science in Robotics and has progressed from research engineer to postdoctoral researcher before moving into industry leadership. His work spans practical applications—performance analysis of propeller engines and rigid-body simulations—to cutting-edge research in deep reinforcement learning for object manipulation. An active contributor to the widely used Bullet Physics SDK, he focuses on robustness and performance by fixing memory, rendering and server-side issues that improve simulation reliability. Colleagues value his blend of rigorous academic training and pragmatic engineering that turns complex physical models into deployable systems.
11 years of coding experience
6 years of employment as a software developer
Junior Scholars Program, Junior Scholars Program at Miami UniversityDoctor of Science, Robotics, Doctor of Science, Robotics at ETH ZürichMaster of Science, Computational Science and Engineering, Master of Science, Computational Science and Engineering at ETH Zurich
English, German, Luxembourgish
Github Skills (12)
simulations10
c1710
simulation10
pybullet10
game-development10
c1110
animation10
simulator10
animate10
robotics9
virtual-reality8
kinematics8
Programming languages (3)
Github contributions (5)
bulletphysics/bullet3
Jun 2017 - Sep 2019
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:7 commits, 5 PRs, 5 comments in 2 years 3 months
Contributions summary:Michel primarily focused on bug fixes and optimizations within the Bullet Physics SDK. Their contributions include fixing memory copy issues related to image data in the PyBullet examples, correcting depth value calculations in the TinyRenderer and fixing errors related to discarding fragments, and optimizing code to reduce the number of operations. They also addressed uninitialized variables and memory management issues in the physics server command processing.
bullet-physicscollision-detectionmachine-learningroboticssimulation
ethz-asl/vgn
Jun 2019 - Dec 2022
Real-time 6 DOF grasp detection in clutter.
Contributions:546 commits, 3 PRs, 36 pushes in 3 years 6 months
real-timedofmanipulationroboticspoint-clouds
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.