Sean Silva
Distinguished Software Engineer at EnCharge AI
Mountain View, California, United States
Summary
🤩
Rockstar🎓
Top SchoolSean Silva is a Distinguished Software Engineer with nine years of experience building high-performance systems, compilers, and ML tooling across companies from PlayStation to Google, Waymo, and EnCharge AI. He specializes in MLIR-based compiler backends and runtime work—contributing dead-code-elimination passes and TensorFlow/PyTorch import support to major open-source projects like tensorflow/mlir, IREE, and torch-mlir. Known for bridging low-level assembly and architecture concerns with higher-level ML engineering, he pairs deep technical rigor with clear communication to drive cross-disciplinary projects. Based in Mountain View and now leading engineering in Munich, he repeatedly improves tooling quality and error reporting, making complex compiler internals more robust and debuggable.
9 years of coding experience
11 years of employment as a software developer
Bachelor of Science - BS Mathematics and Computer Science, Bachelor of Science - BS Mathematics and Computer Science at Purdue University
Github Skills (27)
pytorch10
c-language10
python10
machine-learning10
mlr10
intermediate-code10
compiler-design10
compiler-compiler10
lg10
tensorflow10
intermediate-language10
compiler-optimization10
compiler10
cprogramming-language10
tosca9
Programming languages (8)
Github contributions (5)
llvm/torch-mlir
Sep 2021 - Dec 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 & ML Engineer
Back-end Developer & ML EngineerContributions:870 releases, 1028 reviews, 176 commits in 1 year 3 months
Contributions summary:Sean primarily focused on implementing changes to support the PyTorch ecosystem within the MLIR framework, particularly for the Torch-MLIR project. Their work involved importing PyTorch JIT IR, implementing Python-based relayout functionality, and adding support for new operations like `min`, `max`, and `clamp` within the conversion process. Furthermore, the user contributed by integrating new backends like TOSA and working on a new shape library design, demonstrating a focus on expanding the system's capabilities and improving the overall performance of the compiler.
pytorchmlirtorchcompilerecosystem
iree-org/iree
Nov 2019 - Jan 2023
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:111 reviews, 83 commits, 46 PRs in 3 years 2 months
Contributions summary:Sean primarily contributed to the IREE ML compiler, adding support for TensorFlow SavedModel import into the Flow dialect. This involved implementing features for handling global tensors and variables within the TensorFlow import pipeline, as well as improving the end-to-end testing capabilities. The user also added new tests for models with dynamic shapes and control flow, along with fixes for import stability and error reporting.
mlirspirvvulkantensorflowcompiler
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.