Sumedh ड
AI Research Scientist at Indian Institute of Technology, Bombay
Pune District, Maharashtra, India
Summary
👤
Senior🎓
Top SchoolSumedh ड is an AI Research Scientist and neuromorphic computing specialist with 11 years of experience bridging algorithm–architecture co-design and applied research at Intel and Intel Labs. He holds a PhD in Chemical and Biomolecular Engineering from Johns Hopkins and has translated a foundation in physics and simulation into spiking-neural hardware research, contributing to both theory (Berkeley visiting scholar) and device-aware algorithms. At Intel he focuses on neuromorphic R&D and mentors as Honorary Visiting Faculty at IIT Bombay, blending academic scholarship with product-minded engineering. His open-source contributions to Lava (the neuromorphic computing framework) show practical backend work on ProcessModel decorators and precision-aware LIF implementations, highlighting attention to numerical fidelity across floating- and fixed-point regimes. Comfortable across C++, Python and simulation toolchains from CUDA to COMSOL, he brings a rare mix of chemical-engineering rigor, computational neuroscience insight, and production-oriented software craftsmanship.
11 years of coding experience
17 years of employment as a software developer
Johns Hopkins UniversityIndian Institute of Technology Bombay
Marathi, English, Hindi, German, Persian, Sanskrit
Github Skills (9)
neural-network10
deep-learning10
python10
morph10
web-framework9
fixed8
unit-testing8
fixed-point8
fixed-width8
Programming languages (3)
Github contributions (5)
lava-nc/lava
Nov 2021 - Oct 2022
A Software Framework for Neuromorphic Computing
Role in this project:
Back-end Developer
Back-end DeveloperContributions:107 reviews, 19 commits, 36 PRs in 11 months
Contributions summary:Sumedh primarily contributed to the development of the `@tags` decorator, which is used to categorize and distinguish `ProcessModel` classes within the neuromorphic computing framework. They fixed issues related to the decorator's functionality, particularly concerning subclassing and inheritance. The user's commits also involved refactoring and improvements to the LIF and TernaryLIF process models, specifically addressing issues with floating-point and fixed-point precision. The contributions show an understanding of how to use and extend Lava's ProcessModel for different numerical representations.
neurosciencepythondeep-learningneural-networksmachine-learning
srrisbud/lava-optimization
Nov 2021 - Feb 2025
Constraint Optimization with Lava
Contributions:112 pushes, 19 branches in 3 years 3 months
lavaoptimizationconstraintconstraint-programmingconstraint-optimization
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.