Daniel Noronha
Principal Machine Learning Engineer at AMD
Vancouver, British Columbia, Canada
Summary
🤩
Rockstar🎓
Top SchoolDaniel Noronha is a machine learning engineer with 11 years of experience specializing in accelerating ML workloads from research to product. He has driven productization of model-to-hardware toolchains—co-leading GroqFlow at Groq and now contributing ML systems at AMD—while shipping performance wins for vision and NLP models like BERT, RoBERTa, ViT, and DETR. His PhD from UBC focused on debugging and understanding AI training on advanced architectures, and he published a popular open-source toolchain (500+ stars) that maps TensorFlow computations to hardware. Past roles at Microsoft Project Brainwave and in HPC broadened his expertise in emulation, FPGA/accelerator tooling, and parallel performance tuning. Based in Vancouver, he blends deep hardware-aware ML knowledge (BFP quantization, distillation, sparsity exploitation) with a product-minded approach to developer velocity. Colleagues rely on him to turn complex compiler and systems research into shipping, maintainable software.
11 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Engineering, Doctor of Philosophy - PhD, Computer Engineering at The University of British ColumbiaFederal University of Rio Grande do NorteExchange, Computer Engineering, Exchange, Computer Engineering at Technische Universität BerlinExchange, Computer Engineering, Exchange, Computer Engineering at Rensselaer Polytechnic Institute
English, German, Portuguese
Github Skills (71)
benchmark10
gpu10
openai-api10
onnx10
llm-inference10
ai10
mistral10
vulkan10
localai10
llama10
amd10
genai10
discord10
llm10
onnxruntime10
Programming languages (12)
Github contributions (5)
danielholanda/LeBug
Apr 2020 - Mar 2021
Contributions:260 commits in 11 months
danielholanda/LeFlow
Jun 2018 - Jan 2019
Enabling Flexible FPGA High-Level Synthesis of Tensorflow Deep Neural Networks
Contributions:36 commits, 2 PRs, 31 pushes in 6 months
deep-neural-networksfpgatensorflow
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.