Aleksandr Malyshev
Principal Software Engineer AI ML at AMD
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolAleksandr Malyshev is a Staff/Principal-level software engineer specializing in AI acceleration, deep learning inference, and compiler/toolchain work, with a Master's in Mathematics and two decades of experience across FPGA, ASIC, CPU and GPU platforms. He has driven LLM and model-performance optimizations at AMD and Meta, implemented ROCm/Triton kernels and compiler adaptations, and led ML benchmarking and cluster telemetry efforts at CoreWeave. Comfortable in C/C++, Python, PyTorch/TensorFlow and compiler stacks (LLVM, TVM, MLIR), he focuses on squeezing latency and throughput from hardware while keeping production reliability front-of-mind. His background uniquely blends low-level compiler engineering for custom accelerators (Project Brainwave) with large-scale AI infrastructure and benchmarking, making him equally at home in silicon-aware optimization and distributed cluster observability. Based in Seattle, he prefers US-based, full-time roles and avoids startup/contract work.
2 years of coding experience
15 years of employment as a software developer
specialist Calculating Mathematics and Cybernetics, specialist Calculating Mathematics and Cybernetics at State University of Nizhni Novgorod named after N.I. Lobachevsky (UNN)
Github Skills (20)
pytorch10
llama10
inference10
tpu10
amd10
llm10
triton10
code-generation10
mlops10
llmops10
xpu10
cuda10
transformer10
gpt10
programming-language9
Programming languages (3)
Github contributions (5)
maleksan85/vllm
May 2024 - Jul 2024
A high-throughput and memory-efficient inference and serving engine for LLMs
Contributions:17 pushes, 1 branch in 1 month
maleksan85/scripts
Nov 2024 - Jan 2025
Contributions:2 pushes in 2 months
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.