Alina Sbîrlea
Staff Software Engineer at Google
Mountain View, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAlina Sbîrlea is a Staff Software Engineer in Mountain View with 13 years of deep expertise in compiler back-ends, performance engineering, and ML runtimes, currently driving low-level systems work at Google. She holds a Ph.D. in Computer Science from Rice University and combines academic rigor with production-grade engineering, having optimized code generation and vectorization across projects like LLVM/Clang, Halide, and the XLA compiler. Her open-source contributions include improving compiler diagnostics and lowering passes for the experimental Carbon language, adding SIMD and architecture-specific tests to the LLVM test suite, and managing LLVM integrations within TensorFlow and its runtime—demonstrating both code-level refactors and dependency stewardship. Comfortable in C++ and compiler internals, she has a track record of converting research ideas on heterogeneous and multicore execution into concrete optimizations used in large codebases. An understated strength is her ability to bridge research, testing, and build-system maintenance, ensuring new compiler features land reliably in complex ecosystems.
13 years of coding experience
6 years of employment as a software developer
Ph.D., Computer Science, Ph.D., Computer Science at Rice UniversityBachelor of Science (B.Sc.), Computer Science, Bachelor of Science (B.Sc.), Computer Science at Universitatea „Politehnica” din București
French, Romanian, English
Github Skills (36)
dependency-management10
programming-language10
performance-monitor10
c-language10
dsl10
testing10
llvm10
build-system10
lang10
loop-unrolling10
compiler-compiler10
performance-analysis10
tensorflow10
compiler10
simd10
Programming languages (6)
Github contributions (5)
llvm/llvm-test-suite
Jul 2016 - Aug 2017
Role in this project:
Back-end Developer / Performance Engineer
Back-end Developer / Performance EngineerContributions:17 commits in 1 year 1 month
Contributions summary:Alina primarily contributed to the test suite, specifically focusing on bitcode tests related to SIMD operations and benchmarks. Their work involved creating and modifying C++ code, including driver files and headers, to test and validate SIMD instructions. They also added new tests for different architectures, such as AArch64 and ARM, and updated the build process to improve efficiency and address TBAA verification failures.
openxla/xla
Oct 2017 - Oct 2022
A machine learning compiler for GPUs, CPUs, and ML accelerators
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:9 commits in 5 years
Contributions summary:Alina's contributions primarily involve optimizing the XLA compiler, specifically focusing on improving code generation and performance for specific operations like DynamicUpdateSlice and Dot. They addressed bugs and implemented optimizations related to dynamic slicing and memoization for matrix multiplication. Further, the user is involved in debugging and refactoring tests and optimizing Dot product operations with constant tensors, indicating a focus on improving compilation efficiency.
compilercommunity-drivenmachine-learningmodular
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.