Ben Sanders
E-commerce Operations Manager
Katy, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolBen Sanders is an e-commerce operations leader with 14 years of experience optimizing fulfillment, forecasting, inventory and P&L across enterprise and mid-market environments. Currently managing AMD’s Direct-to-Consumer operations for NA and EU, he combines hands-on vendor and back-end system management with cross-functional partnerships in marketing, logistics and customer service to improve end-to-end customer experience. He has a track record of driving migrations and process automations that measurably boost KPI performance and resource efficiency, and he builds dashboards and forecasting tools to turn data into faster decisions. Uncommonly for an ops leader, Ben also contributes to high-performance computing open-source projects (ROCm stack), bringing systems-level engineering exposure that informs his focus on performance, memory management and robust tooling. An MBA from Baylor complements his analytic approach and people-first leadership style.
14 years of coding experience
2 years of employment as a software developer
Master, Business Administration, 3.83, Master, Business Administration, 3.83 at Baylor University - Hankamer School of BusinessBachelor of Arts, History, 3.78, Bachelor of Arts, History, 3.78 at The University of Texas at Austin
English, Spanish
Github Skills (20)
opencl10
assembly10
c-language10
matrix-multiplication10
memory-management10
blas10
hip10
roc10
performance-optimization10
assemble10
assembler10
contraction10
cprogramming-language10
testing9
debug9
Programming languages (7)
Github contributions (5)
ROCm/Tensile
Feb 2018 - Apr 2020
Stretching GPU performance for GEMMs and tensor contractions.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1228 commits, 362 PRs, 156 pushes in 2 years 2 months
Contributions summary:Ben contributed to the core functionality of the project, primarily focusing on improving matrix multiplication and tensor contraction performance. Their work involved adding tests for the pack_tensor_dims functionality and fixing issues related to handling multiple summation dimensions, particularly within the assembly code. The user also refactored and optimized the store path, demonstrating a focus on performance improvements for the target library.
amdpythontensorhipauto-tuning
ROCm/hip
Jan 2016 - Dec 2020
HIP: C++ Heterogeneous-Compute Interface for Portability
Role in this project:Back-end Developer & Systems Engineer
Back-end Developer & Systems EngineerContributions:654 commits, 83 PRs, 57 pushes in 4 years 11 months
Contributions summary:Ben primarily focused on adapting the HIP (Heterogeneous-Compute Interface for Portability) library to work with the HCC (Heterogeneous Compute Compiler) environment, enhancing the codebase with new functionalities. They addressed compilation issues, implemented functionalities like peer-to-peer copies using the accelerator views, and implemented host memory registration. Their work involved incorporating changes to improve memory management, and kernel execution within the HCC framework, and enhance integration for more performant memory copies.
cudaheterogeneousgpuportabilityhip-runtime
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.