Prateek Gupta - Principal Engineer, Compilers at GlobalFoundries

Prateek Gupta

Principal Engineer, Compilers at GlobalFoundries

Bengaluru, Karnataka, India

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Prateek Gupta is a Principal Engineer specializing in ML compilers with nine years of experience building compiler infrastructure to accelerate AI/ML workloads, currently driving compiler work at GlobalFoundries after a stint integrating and optimizing Torch-MLIR at Cerebras. He has deep hands-on expertise with MLIR and LLVM, has optimized TensorFlow operations via MLIR, and contributed substantive back-end work to the high-profile llvm/torch-mlir project translating PyTorch aten ops into MLIR linalg. Comfortable across C/C++ and Python, he pairs systems-level compiler engineering with practical ML experience (NLP, supervised learning, clustering) and has built profiling and Dask-based tooling to diagnose and scale real workloads. Known for shipping production-focused lowerings and kernel mappings, he brings a rare combination of compiler internals knowledge and applied ML performance engineering.

8 years of coding experience

5 years of employment as a software developer

Indian Institute of Technology Delhi (IIT Delhi)

All India Secondary School Certificate, All India Secondary School Certificate at Bishop Conrad School

Bachelors of Technology Software Engineering, Bachelors of Technology Software Engineering at Delhi Technological University

Delhi Public School - R. K. Puram

English, Hindi

Github Skills (5)

compiler10

pytorch10

compiler-compiler10

mlr10

python8

Programming languages (4)

C++LLVMJupyter NotebookPython

Github contributions (5)

llvm/torch-mlir

Oct 2021 - Jul 2022

The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

Role in this project:

Back-end Developer

Contributions:46 reviews, 16 commits, 30 PRs in 8 months

Contributions summary:Prateek primarily contributed to the Torch-MLIR project, focusing on adding end-to-end (E2E) support for various PyTorch operations, translating them to the MLIR ecosystem. Their work involved implementing lowering from aten (PyTorch's internal operators) to linalg, creating new operations within the aten dialect, and refactoring code. The commits showcase the user's ability to work with MLIR and PyTorch's internal representations.

pytorchmlirtorchcompilerecosystem

gprateek93/Sikka--A-Simple-Bitcoin-Implementation

Jun 2020 - Jul 2020

Contributions:50 commits, 5 pushes in 27 days

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.

Request Free Trial