Kevin Arvai
Senior Engineer, Machine Learning at BTI360
Alexandria, Virginia, United States
Summary
👤
Senior🎓
Top SchoolKevin Arvai is a Principal Engineer and data scientist with 11+ years of experience applying machine learning and deep learning to clinical genomics and molecular diagnostics. He has led teams and built production-grade ML solutions—from multimodal cancer classifiers and qPCR deep-learning algorithms to NLP pipelines that cut clinical curation time—while authoring reusable Python packages adopted across cross-functional teams. A longtime open-source advocate, he develops and maintains Imputer for genome imputation and regularly contributes Kaggle kernels and GitHub projects that bridge research and production. Based in Alexandria, VA, he combines hands-on HPC and cloud optimization with domain expertise in bioinformatics, and his background as a histotechnologist gives him rare end-to-end perspective from lab assays to deployed ML.
11 years of coding experience
15 years of employment as a software developer
Certificate Histologic Technology/Histotechnologist, Certificate Histologic Technology/Histotechnologist at Indiana University BloomingtonDeep Learning Nanodegree Artificial Intelligence, Deep Learning Nanodegree Artificial Intelligence at UdacityBachelor of Science (B.S.) Biology General, Bachelor of Science (B.S.) Biology General at Lycoming CollegeMaster of Science (M.S.) Biomathematics Bioinformatics and Computational Biology, Master of Science (M.S.) Biomathematics Bioinformatics and Computational Biology at George Mason University
Stackoverflow
8,075reputation
1.3mreached
91answers
12questions
scikit-learn
top-1%
machine-learning
top-5%
python
top-1%
twitter
top-5%
csv
top-5%
numpy
top-5%
Github Skills (147)
python10
synthetic10
forge10
tabular10
genomics10
genomics-visualization10
scientific-computing10
genes10
dimensionality-reduction10
scikit10
statistics10
imputation10
genetic10
synthetic-data10
multi-table10
Programming languages (6)
Github contributions (5)
GeneDx/phenopy
Jan 2019 - Mar 2021
Phenotype comparison tools using semantic similarity.
Contributions:11 releases, 4 reviews, 324 commits in 2 years 2 months
semantic-similarityphenomicscomparisonhposimilarity
arvkevi/clinvar-kaggle
Apr 2018 - Mar 2020
Scripts related to the ClinVar conflicting classifications dataset on Kaggle
Contributions:25 commits, 4 PRs, 17 pushes in 1 year 11 months
kaggleclassificationsdatasetmachine-learningclinvar
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.