Alex Gladyshev
Software Engineer at Duos
Tbilisi, Georgia
Summary
🤩
RockstarAlex Gladyshev is a software engineer based in Tbilisi, Georgia with nine years of hands-on experience building and integrating ML tooling and runtime components. He has contributed to high-profile open-source projects like ONNX Runtime and Apache TVM, improving TVM execution provider integration, CI, and converters for advanced ops such as FastGelu and QAttention. At Duos (current) and previously at Lifter.ai, he focused on making ML inference workflows more reliable and testable, including adding iOS simulation support for RPC testing. Alex combines systems-level engineering with practical developer tooling improvements—often upstreaming tests, documentation, and build refinements that ease adoption. Notably, his work spans both low-level runtime integration and converter-level model compatibility, reflecting a rare mix of compiler/infra and ML model deployment experience.
10 years of coding experience
1 year of employment as a software developer
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (17)
python10
machine-learning10
onnx10
rpc10
deep-learning10
ios9
cicd9
hardware-acceleration9
cprogramming-language8
c-language8
tensor7
deeplearning-ai7
compiler-compiler7
compiler7
docker6
Programming languages (6)
Github contributions (5)
microsoft/onnxruntime
Jan 2022 - Sep 2022
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
ML Engineer
ML EngineerContributions:28 reviews, 27 commits, 5 PRs in 7 months
Contributions summary:Alex primarily worked on enhancing the TVM (Tensor Virtual Machine) Execution Provider (EP) integration within the ONNX Runtime. Their contributions included adding tests, integrating the TVM EP into the CI pipeline, and updating documentation. They also focused on implementing support for various data types within the TVM EP and refining the build process and related scripts for the TVM EP integration. Their work demonstrates a focus on improving the usability and integration of the TVM EP within the ONNX Runtime.
machine-learningonnxruntimedeep-learningonnxneural-networks
apache/tvm
Jun 2021 - Jan 2023
Open Machine Learning Compiler Framework
Role in this project:ML Engineer
ML EngineerContributions:36 reviews, 10 commits, 10 PRs in 1 year 7 months
Contributions summary:Alex made significant contributions to the RPC and ONNX converter functionalities within the TVM repository. They added support for iOS simulation in the RPC framework, enabling testing and tuning capabilities on iOS devices. Moreover, the user implemented and extended ONNX converters for FastGelu and QAttention operations, enhancing the model conversion capabilities of TVM. They also added and updated tests for the new features, along with code refactoring and fixing of existing code.
compilermachine-learningtensordeep-learninggpu
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.