Jayaram Bobba
Software Engineer at Intel Corporation
Portland, Oregon, United States
Summary
🤩
Rockstar🎓
Top SchoolJayaram Bobba is a seasoned Deep Learning Software Engineer with nine years of professional experience, currently focused on machine learning framework and platform engineering at Intel in Portland, Oregon. He holds advanced degrees from the University of Wisconsin–Madison and a BTech in Computer Science from IIT Madras, blending strong academic research roots—formerly working on transactional memory and hardware-software co-design—with practical production engineering. Notably, he contributed significant MKLDNN-based convolution support to Intel’s nGraph project, optimizing CPU deep learning kernels and broadening data-format compatibility for real-world workloads. Jayaram pairs low-level performance tuning and C++ systems work with an ML-centric perspective, making him effective at bridging research ideas into high-performance, production-ready runtimes. Colleagues describe him as a meticulous problem-solver who quietly advances core infrastructure that others rely on in deployed AI systems.
9 years of coding experience
5 years of employment as a software developer
Indian Institute of Technology MadrasMaster of Science, Computer Sciences, Master of Science, Computer Sciences at University of Wisconsin-Madison
Github Skills (10)
convolution10
c-language10
deep-learning10
cprogramming-language10
performance-optimization10
back-end-development9
intel7
architecture7
computer-architecture7
cpu-architecture7
Programming languages (2)
Github contributions (5)
NervanaSystems/ngraph
Jan 2018 - Mar 2020
nGraph - open source C++ library, compiler and runtime for Deep Learning
Role in this project:
Back-end Developer
Back-end DeveloperContributions:227 commits, 171 PRs, 371 pushes in 2 years 2 months
Contributions summary:Jayaram significantly contributed to the implementation of MKLDNN convolution features within the nGraph Deep Learning compiler, runtime, and library. They integrated and utilized MKLDNN (Intel's Math Kernel Library for Deep Neural Networks) for optimized convolution operations, particularly for CPU backends. Their work involved adding support for various convolution types, including bias operations and applying optimizations to the internal kernels of the system, as well as adding support for various data formats.
inference-enginecppc-librarydeep-learningtvm
NervanaSystems/ngraph-python
Feb 2017 - Nov 2017
Original Python version of Intel® Nervana™ Graph
Contributions:130 commits in 8 months
pythoninteloneapigraphpython-version
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.