Summary
Martin Ethier is an ML engineer and MASc candidate at the University of Waterloo with nine years of hands-on experience building perception and simulation systems for autonomous vehicles and robotics. He has shipped simulation-driven training pipelines and domain-randomization tools (Unity/C#) to generate data for object detection and ground segmentation, and has trained production-grade models such as YOLOv7 for forklift detection. His research blends sim-to-real lane detection and LiDAR/3D perception, resulting in a co-authored IV2022 paper and applied tools for semantic labeling and visualization. Comfortable across PyTorch, TensorFlow, ROS, and MLOps stacks, he also led R&D for continuous training pipelines at DarwinAI and prototyped industrial imaging and spectral ML solutions. Colocated in Waterloo, he pairs academic research with practical deployment experience—often turning simulators and visualization tooling into datasets and models that match real-world performance.
8 years of coding experience
2 years of employment as a software developer
Master of Applied Science (MASc), Electrical and Computer Engineering, Master of Applied Science (MASc), Electrical and Computer Engineering at University of Waterloo
English, French