Enrico Pelos
Director Of Engineering at Arm
Greater Nice Metropolitan Area France
Summary
🤩
Rockstar🎓
Top SchoolEnrico Pelos is a Director of Engineering based in the Greater Nice area with 11 years of leadership in semiconductor and systems engineering, currently steering teams at Arm. He combines deep hands-on technical roots from VHDL and digital front-end design through SoC program management at Infineon and Intel with strategic operational leadership across multi-site R&D and product-scale delivery. At Arm he has progressed from operations and program roles into engineering leadership, reflecting a knack for translating complex hardware-software requirements into reliable, production-ready systems. He also contributes to high-profile open-source ML infrastructure—optimizing the WebNN execution provider in Microsoft's ONNX Runtime—showing ongoing engagement with ML inferencing performance and cross-platform acceleration. Known for bridging rigorous engineering discipline with pragmatic project execution, he brings a practical blend of low-level design expertise and large-team management.
11 years of coding experience
24 years of employment as a software developer
Master's degree Electronic Engineering, Master's degree Electronic Engineering at Università degli Studi di Palermo
English, French, Italian
Github Skills (9)
machine-learning10
hardware-acceleration10
onnx9
javascript9
typescripts8
typescript8
typescript-types8
deep-learning7
webassembly6
Programming languages (8)
Github contributions (5)
microsoft/onnxruntime
Jan 2024 - Mar 2025
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
ML Engineer
ML EngineerContributions:41 reviews, 7 PRs, 61 comments in 1 year 1 month
Contributions summary:Enrico's contributions center on enhancing the WebNN (Web Neural Network) Execution Provider (EP) within the ONNX Runtime. They've implemented features to enable MLTensor-based input/output bindings, cache MLTensors for improved performance, and optimize data transfer from CPU to ml-tensor. Additionally, they've addressed caching issues and corrected logic related to MLTensor shape matching, showcasing a focus on WebNN EP functionality and optimization.
runtimetrainingtensorflowai-frameworkaccelerator
egalli/onnxruntime
May 2024 - Mar 2025
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Contributions:55 pushes, 10 branches in 10 months
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.