Aamir Raihan
Software Engineer 2 at Microsoft
Vancouver, British Columbia, United States
Summary
👤
Senior🎓
Top SchoolAamir Raihan is a Software Engineer 2 based in Vancouver with eight years of experience at the intersection of systems and machine learning, currently building efficient algorithms and infrastructure for ML at Microsoft. He brings deep compiler and hardware-aware software expertise from Huawei, where he helped design a tensor language, implemented key operators and optimized compiler front-ends to cut compilation time by ~60%, and developed high-performance kernels for AI chips. His background spans GPU simulation and low-level kernel work—he has contributed tensor-core and WMMA support and deadlock fixes to the widely used GPGPU-Sim project—plus earlier roles in SoC design and verification at NXP and Freescale. Aamir pairs rigorous academic training (UBC M.Eng with top grades) with hands-on systems engineering, often translating research insights into production-quality implementations. He has a track record of bridging SIMT/CUDA and SIMD/compiler targets, reflecting a practical knack for co-design across algorithms, compilers, and hardware.
8 years of coding experience
6 years of employment as a software developer
Master's degree, Computer Engineering, 4.30/4.33, Master's degree, Computer Engineering, 4.30/4.33 at UBC Electrical and Computer EngineeringIntermediate/+2, Mathematics and Science, 86%, Intermediate/+2, Mathematics and Science, 86% at Mahendra Muni Saraswati Shishu Vidhya Mandir,MadhupurBachelor of Technology (B.Tech.), Electrical and Electronics Engineering, 8.56 CGPA, Bachelor of Technology (B.Tech.), Electrical and Electronics Engineering, 8.56 CGPA at Indian Institute of Technology (Banaras Hindu University), VaranasiICSE, 94%, ICSE, 94% at Carmel School
Github Skills (5)
cuda10
c-language10
cprogramming-language10
gpu10
assembly8
Programming languages (5)
Github contributions (5)
gpgpu-sim/gpgpu-sim_distribution
May 2018 - Feb 2019
GPGPU-Sim provides a detailed simulation model of contemporary NVIDIA GPUs running CUDA and/or OpenCL workloads. It includes support for features such as TensorCores and CUDA Dynamic Parallelism as well as a performance visualization tool, AerialVisoin, and an integrated energy model, GPUWattch.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:46 commits, 3 PRs, 18 comments in 8 months
Contributions summary:Aamir's commits primarily focus on modifications to the gpgpu-sim project, specifically implementing and debugging features related to tensor core operations, including wmma (warp matrix multiply-accumulate) instructions. The contributions involve adding and modifying code within the instructions, ptx_ir, and cuda-sim files to support wmma load, store and mma instructions. The user added various wmma operation examples in different layouts and data types and resolved a deadlock issue in one of the kernels.
simsimulationgpgpuopenclnvidia
AamirRaihan/SWAT
Oct 2020 - Jan 2021
Contributions:4 commits, 20 pushes, 1 branch in 2 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.