Edward Shogulin is a Principal Engineer based in Ireland with over a decade of professional software experience and six years focused on deep learning and ML inference engineering. He led low-precision transformation design and JIT code generation for ARM64 and RISC-V at Intel, and now continues driving architecture and delivery at Huawei. Edward is an active contributor to the highly regarded OpenVINO open-source toolkit, implementing advanced multichannel concat and per-channel scaling optimizations that improve ML model inference performance. His background spans embedded and distributed systems, real-time trading infrastructure, and developer tooling, giving him a rare cross-domain fluency from low-level codegen to production ML pipelines. Colleagues rely on him for technical ownership of compiler backends and pragmatic designs that bridge research-grade algorithms and deployable systems. He blends deep systems expertise with a practical focus on test infrastructure and measurable inference optimizations.
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & ML Engineer
Contributions:978 reviews, 97 commits, 512 PRs in 2 years 6 months
Contributions summary:Edward contributed to the OpenVINO toolkit by implementing complex concat graph support, including multichannel concat and scale per channel support, and improving test infrastructure. The commits demonstrate expertise in optimizing and deploying AI inference, specifically within the context of low precision transformations. The changes directly address optimization techniques related to machine learning models and inference engines.
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.