Ken Larrey

Data Science Specialist

Greater Boston United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Ken Larrey is a Data Science Specialist at McKinsey with 11 years of experience applying analytical rigor to real-world business problems and shipping production-ready ML solutions. Trained in both electrical engineering and economics at Duke, he blends quantitative modeling, software engineering, and product-minded pragmatism to translate complex data into actionable insight. At McKinsey he has progressed from advisor to specialist, pairing client-facing strategy work with hands-on implementation. He’s also contributed to the popular Gensim project—making word2vec deterministic and more reproducible—showing a commitment to dependable, research-grade tooling. Based in Greater Boston, Ken thrives at the intersection of reproducible ML research and enterprise delivery.
code11 years of coding experience
job1 year of employment as a software developer
bookBachelor of Science (B.S.), Electrical and Electronics Engineering, Bachelor of Science (B.S.), Electrical and Electronics Engineering at Duke University
bookHigh School, High School at St. John's School, Houston TX
github-logo-circle

Github Skills (7)

word-embeddings10
gensim10
topic-modeling10
nlp10
python10
data-science9
machine-learning9

Programming languages (2)

CythonPython

Github contributions (5)

github-logo-circle
piskvorky/gensim

Sep 2014 - May 2015

Topic Modelling for Humans
Role in this project:
userML Engineer
Contributions:9 commits, 2 PRs, 16 comments in 7 months
Contributions summary:Ken primarily focused on improving the Gensim library's word2vec implementation. Their contributions centered around introducing deterministic initialization for word vectors, allowing for reproducible results across different training runs and datasets. They also refactored the code to use built-in hash functions instead of external libraries and made minor comment and spacing adjustments, and removed obsolete code parameters.
pythonword-similarityword-embeddingsdata-miningfor-humans
KCzar/BulkFindReplace

Oct 2016 - Oct 2016

Contributions:4 pushes, 1 branch, 1 tag in 1 day
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.
Request Free Trial