Summary
Hashim Sharif is a Senior Member of Technical Staff at AMD Research with 11 years of experience building software infrastructure that makes AI accelerators feel simple and powerful. He works at the intersection of compilers, runtimes, and high-performance libraries to unlock specialized hardware, recently focusing on software stacks for processing-in-memory and AI Engine Array architectures. His PhD and subsequent research at UIUC produced open-source compiler tooling (ApproxHPVM, ApproxTuner) and publications in OOPSLA and PPoPP, reflecting a strong track record of production-ready research. Hashim has a history of practical systems work—from UVM GPU optimizations at Argonne to software debloating and static-analysis tools—demonstrating an ability to translate deep compiler research into measurable performance gains. Based in Champaign, IL, he combines academic rigor with industry impact, often targeting resource-constrained and application-aware optimization scenarios that are easy to overlook but critical for deployed AI systems.
10 years of coding experience
8 years of employment as a software developer
University of Illinois Urbana-Champaign
Bachelor of Science (B.S.), Computer Science, Bachelor of Science (B.S.), Computer Science at National University of Computer and Emerging Sciences