Pruthvi Gowda
Senior Software Engineer at Microsoft
Kirkland, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolPruthvi Gowda is a Senior Software Engineer with nine years of experience building and optimizing ML runtimes and inference platforms, currently developing a cross-platform C++17 client runtime and distributed inference service for Office AI at Microsoft. Previously at Intel AI he was a top contributor to the nGraph compiler, implementing and performance-tuning fused kernels (BatchNorm, Sigmoid, LSTM, etc.), MLIR lowering, and concurrent execution strategies that accelerated RNNs by ~40%. He blends low-level systems and compiler work with production service engineering, focusing on CPU backends, graph compilers, and scalable ML microservices. Based in Kirkland, WA, he pairs strong academic credentials (MS ECE, 4.0 GPA) with practical expertise in DNNL/MKLDNN, Intel TBB, and TensorFlow grappler passes. An avid open-source contributor, his nGraph improvements reflect a rare combination of algorithmic understanding and hands-on kernel optimization.
9 years of coding experience
8 years of employment as a software developer
The University of ArizonaSSLC, 10th Standard, 90.40%, SSLC, 10th Standard, 90.40% at Holy Crescent English School (Karnataka State Board)Bengaluru UniversityPre University College, Physics , Chemistry , Mathematics , Biology, PCM ( 98.7%), Pre University College, Physics , Chemistry , Mathematics , Biology, PCM ( 98.7%) at Government Boys College
English, Kannada, Hindi
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (16)
neural-network10
algorithm10
numerical-optimization10
code-optimization10
graph10
machine-learning10
algorithms10
c-language10
deep-learning10
cprogramming-language10
batch-normalization10
optimisation10
optimization10
python5
tensorflow4
Programming languages (3)
Github contributions (5)
NervanaSystems/ngraph
Feb 2018 - May 2020
nGraph - open source C++ library, compiler and runtime for Deep Learning
Role in this project:
Back-end Developer & Machine Learning Engineer
Back-end Developer & Machine Learning EngineerContributions:208 commits, 95 PRs, 502 pushes in 2 years 3 months
Contributions summary:Pruthvi's contributions primarily revolve around the integration of Batch Normalization (BN) and Sigmoid activation within the nGraph compiler for Deep Learning. They developed and implemented pattern matchers and optimized code for fused operations, particularly for BN and its backpropagation, along with supporting the new BatchNormInference operator. The user demonstrated the ability to write and integrate optimized MKLDNN kernels for various operations like LRN, with a focus on improving performance. Their work included contributions to a new RNN framework and optimizing different aspects of the compute graph.
inference-enginecppc-librarydeep-learningtvm
pruthviIntel/mlir
Dec 2019 - Dec 2019
"Multi-Level Intermediate Representation" Compiler Infrastructure
Contributions:1 PR, 15 pushes, 2 branches in 21 days
representationmulti-levelinfrastructurelevel-intermediatecompiler
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.