Gratian Lup is a Senior Compiler Engineer with 13 years of low-level and systems programming experience, currently optimizing the CUDA compiler at NVIDIA. He previously led major backend and toolchain performance work at Microsoft, driving a migration to an SSA-based optimizer, implementing advanced optimizations (CSE/PRE, jump threading, redundant store elimination) and delivering dramatic linker/PDB and LTCG speedups for large AAA games. His expertise spans MLIR/LLVM backends for AI accelerators as well as profiling-driven performance tuning across compiler, linker, and debug-info components. Notably, he built testing infrastructures and integrations (Souper, Alive) to catch real-world regressions and prototype high-impact optimizations before production rollout. Based in Seattle, he combines deep algorithmic rigor with pragmatic engineering that measurably improves both generated code quality and developer iteration time.
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.