Benjamin Fineran
Washington DC-Baltimore Area United States
Summary
🤩
Rockstar🎓
Top SchoolBenjamin Fineran is a high-energy machine learning engineer with a decade of experience building teams, products, and algorithms that speed up and reduce the cost of ML deployments across industries. He leads pragmatic, production-focused teams and has deep hands-on expertise in sparsity-aware inference—contributing significantly to the widely used DeepSparse runtime and integrations with Hugging Face Transformers. A former engineer at Google and Facebook Applied Machine Learning, Benjamin focuses on practical solutions in telecommunications, climate tech, and defense while balancing research-grade rigor with engineering velocity. He holds BSE and MSE degrees from UPenn and is based in the Washington DC–Baltimore area, where he continues to drive ML at scale through open-source work and platform-minded product leadership.
10 years of coding experience
Montgomery Blair High SchoolBachelor of Science in Engineering - BSE, Bachelor of Science in Engineering - BSE at University of Pennsylvania
Github Skills (13)
mle10
sparse10
benchmarking10
benchmark10
deep-learning10
onnx10
python10
ml10
machine-learning9
inference9
huggingface-transformers9
compile8
compilation8
Programming languages (3)
Github contributions (5)
neuralmagic/deepsparse
Jan 2021 - Jan 2023
Role in this project:
ML Engineer
ML EngineerContributions:1593 reviews, 177 commits, 502 PRs in 2 years
Contributions summary:Benjamin primarily contributed to improving the DeepSparse framework for sparsity-aware deep learning inference, specifically for the `deepsparse` package. Their commits show a focus on enhancing model compilation, providing tools for benchmarking, adding progress bars, and integrating SparseZoo models, facilitating the efficient execution of sparse models on CPUs. Furthermore, they improved the integration with the Hugging Face Transformers library.
llm-inferenceruntimetensorflowsparsificationmachinelearning
neuralmagic/sparsezoo
Jan 2021 - Nov 2022
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
Contributions:438 reviews, 29 commits, 153 PRs in 1 year 10 months
mobilenetsparsedeep-learning-modelsopenmmlabsparsification-recipes
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.