Ashok Emani
Software Engineer
Greater Seattle Area United States
Summary
🤩
RockstarAshok Emani is a software engineer with eight years of experience focused on deep learning infrastructure and performance engineering in the Greater Seattle Area. Currently contributing to Intel’s Artificial Intelligence Products Group, he combines low-level C++ systems work with practical ML integration to accelerate inference and training on Intel architectures. His open-source contributions include enhancing nGraph with command-line tooling and extending MXNet’s MKL-DNN integration and unit testing, demonstrating attention to both developer ergonomics and production performance. He excels at bridging compiler/runtime concerns and higher-level ML frameworks, ensuring optimized, compatible implementations across stacks. Colleagues rely on him for pragmatic refactors that improve reusability and testing coverage, not just feature additions. Outside the obvious, he invests in making examples and tooling more accessible, which amplifies adoption of complex libraries.
8 years of coding experience
Stackoverflow
1reputation
69reached
0answers
1question
Github Skills (13)
testing10
mxnet10
c-language10
deep-learning10
cprogramming-language10
python10
machine-learning9
command-line-interface9
develop8
gluon8
py8
convolutional-neural-networks7
neural-network7
Programming languages (5)
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
Back-end DeveloperContributions:181 commits, 72 PRs, 297 pushes in 2 years 3 months
Contributions summary:Ashok contributed to the `ngraph` repository, a library and compiler for deep learning, by adding sample code to the examples directory. The changes involved adding a new header file which implements CLIPP, a command line interface library for modern C++. Further contributions refactored tools and merged updates from the master branch into the examples directory. These changes indicate the user's involvement in extending the utility of the library.
inference-enginecppc-librarydeep-learningtvm
apache/mxnet
Sep 2017 - May 2018
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Role in this project:ML Engineer
ML EngineerContributions:16 commits, 17 PRs, 122 comments in 8 months
Contributions summary:Ashok primarily contributed to the optimization and enhancement of the MXNet deep learning framework. Their work includes addressing issues related to MKL-DNN (Intel Math Kernel Library for Deep Neural Networks), a library for accelerating deep learning on Intel architectures. The commits involve modifying code to correctly utilize MKL-DNN, improving performance, and ensuring compatibility, particularly in areas like fully connected layers and pooling layers. They also added unittests for Gluon and overall MKLDNN integration.
pythonschedulerdataflowmutationdata-science
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.