Summary
Charitha Saumya is a Deep Learning Compiler Engineer with nine years of experience building high-performance GPU compilers and compiler optimizations for AI workloads, currently at Intel in San Jose. A Purdue PhD student in Computer Engineering, he has a strong research-to-product track record—advancing LLVM/ROCm optimizations, symbolic execution acceleration, and tools that extrapolate worst-case loop behavior for scalability analysis. His internships at Adobe and industry roles demonstrate practical expertise parallelizing AutoML and improving C++/Spark performance, while earlier work spans EDA, distributed file tooling, and performance-sensitive systems. He combines rigorous academic research with production-minded engineering, often focusing on compiler-level transformations that yield measurable GPU and CPU performance gains.
9 years of coding experience
8 years of employment as a software developer
Bachelor of Science - BS, Electronic and Telecommunication Engineering, Bachelor of Science - BS, Electronic and Telecommunication Engineering at University of Moratuwa
Dharmaraja College - Kandy
The Chartered Institute of Management Accountants
Master of Science - MS, Electrical and Computer Engineering, Master of Science - MS, Electrical and Computer Engineering at Purdue University
English