Prachi Gupta
Silicon Design Engineer 2 at AMD
Austin, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolPrachi Gupta is a Silicon Design Engineer with 11 years of experience in VLSI physical and circuit design, currently contributing at AMD after roles in Intel’s EDA and design automation teams. She pairs strong scripting skills (Python, C++, Cadence SKILL, Perl) with hands-on firmware and system-level work—evidenced by contributions to Open Power’s op-build and ROCm-focused PyTorch optimizations. Prachi has driven QoR improvements and built automation tools to streamline CAD workflows and code-quality checks, while deepening expertise in physical design flows and CMOS analysis from an MS at the University of Minnesota. A persistent learner and technical communicator, she documents her engineering journey to inspire other women in hardware and is actively expanding her toolset with TCL and advanced firmware integrations.
11 years of coding experience
2 years of employment as a software developer
Master of Science - MS Electrical and Computer Engineering, Master of Science - MS Electrical and Computer Engineering at University of MinnesotaBachelor of Technology Electronics and Communications, Bachelor of Technology Electronics and Communications at Vellore Institute of Technology
Github Skills (19)
pytorch10
python10
patch10
firmware10
machine-learning10
makefile10
openpower10
roc10
deep-learning10
gpu10
buildroot9
c119
neural-network9
c179
triton9
Programming languages (10)
Github contributions (5)
open-power/op-build
Nov 2016 - Nov 2017
Buildroot overlay for Open Power
Role in this project:
Back-end Developer & Firmware Engineer
Back-end Developer & Firmware EngineerContributions:28 commits, 48 PRs, 19 pushes in 11 months
Contributions summary:Prachi's commits primarily involve modifications to the `hostboot` component within the `op-build` repository, which is a buildroot overlay for Open Power. They are updating code related to the processMRW functionality, including modifications to various configuration files and patch files. Their work is focused on generating witherspoon pnor, which suggests a focus on firmware development and system-level programming within the open power platform. This indicates experience working with build systems and hardware-specific configurations.
firmwareoverlaymakefilebuildrootpower
pytorch/pytorch
Aug 2023 - Mar 2025
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Role in this project:ML Engineer
ML EngineerContributions:3 reviews, 31 PRs, 58 comments in 1 year 7 months
Contributions summary:Prachi primarily contributed to the integration and optimization of PyTorch within the ROCm environment. Their work involved modifying tests to accommodate ROCm-specific configurations, including adding and enabling tests related to the Inductor workflow. They also addressed performance issues by adding conditions for channels last logic and integrating Triton builds for ROCm. Furthermore, the user worked on enabling AOT and CUDA tests on ROCm.
pythongpu-accelerationdeep-learninggpunumpy
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.