Morteza Hosseini
Senior Software Engineer at Browse AI
Greater Vancouver Metropolitan Area Canada
Summary
👤
Senior🎓
Top SchoolMorteza Hosseini is a Senior Software Engineer with 10 years of experience specializing in Generative AI inference and system- and network-level performance optimizations. He has driven production-grade microservices and high-performance data pipelines for SaaS at Browse AI and optimized LLM inference for datacenters at Huawei, while his research work at the University of Calgary applied eBPF and time-series ML to accelerate distributed workloads. A repeat OpenVINO contributor, he implemented and NEON-optimized Scaled Dot Product Attention for ARM with FP16 support and RoPE fusion—work that directly improves GenAI latency on edge devices. He pairs practical backend engineering (Python, Go, Kubernetes) and distributed systems experience with low-level kernel tuning, making him effective across the stack from device kernels to cloud microservices. Based in Greater Vancouver, he blends academic rigor with open-source impact and a personal drive to "break the cycle, rise above."
10 years of coding experience
8 years of employment as a software developer
Bachelor's degree, Computer Software Engineering, Bachelor's degree, Computer Software Engineering at Shahid Beheshti UniversityMaster's degree, Computer Science, Master's degree, Computer Science at University of CalgaryAllame Helli 4
Github Skills (8)
arm10
computer-vision10
ai10
neon9
cprogramming-language9
deeplearning-ai9
c-language9
deep-learning9
Programming languages (11)
Github contributions (5)
openvinotoolkit/openvino
Mar 2024 - Nov 2024
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
ML Engineer
ML EngineerContributions:10 reviews, 10 PRs, 14 comments in 8 months
Contributions summary:Morteza primarily contributed to the OpenVINO toolkit by implementing and optimizing Scaled Dot Product Attention (SDPA) for ARM devices. Their work involved enabling and improving RoPE fusion and integrating NEON vector instructions for enhanced performance. Additionally, the user addressed test failures and added support for FP16 data types within the SDPA implementation.
inference-enginepytorchmodel-optimizerdeep-learninggpu
mory91/openvino
Mar 2024 - Dec 2024
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Contributions:1 PR, 199 pushes, 14 branches in 8 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.