Anthony Kesich
Software Engineer at Recidiviz
New Glarus, Wisconsin, United States
Summary
🤩
Rockstar🎓
Top SchoolAnthony Kesich is a software engineer with 12 years of experience building scalable backend systems and NLP features, currently contributing at Recidiviz from New Glarus, Wisconsin. He holds a Ph.D. in High Energy Nuclear Physics from UC Davis and previously applied that data-heavy, C++-based analysis expertise to petabyte-scale collider datasets. Anthony spent four years at Facebook where he maintained Wit.ai, led work on the M assistant inside Messenger, and did ML engineering for Instagram, and he’s contributed NLP improvements to the well-known Duckling project (including time parsing and INR support). Comfortable across research and product environments, he has taught algorithms at Morgan State and run interview prep and coaching for students. Outside code he brings an unusual mix of practical skills—from campaign organizing that helped elect a state Supreme Court justice to hands-on goat tending—reflecting a pragmatic, systems-oriented mindset.
11 years of coding experience
12 years of employment as a software developer
Master of Science (M.S.), Physics, Master of Science (M.S.), Physics at University of California, DavisBachelor of Science (B.S.), Physics, Bachelor of Science (B.S.), Physics at Massachusetts Institute of Technology
Github Skills (11)
clojure10
nlp10
clojure-cli10
parse9
string-parsing9
regular-expression9
date-parsing9
bump7
bumpversion7
bump2version7
versioning7
Programming languages (5)
Github contributions (5)
facebookarchive/duckling_old
Jul 2015 - Jul 2015
Deprecated in favor of https://github.com/facebook/duckling
Role in this project:
Back-end Developer
Back-end DeveloperContributions:7 commits, 4 PRs, 5 pushes in 1 day
Contributions summary:Anthony primarily contributed to the project by modifying and adding to the natural language processing (NLP) capabilities of the system. Their work centered on refining time-related parsing and adding support for Indian Rupee (INR) currency parsing and formatting within the finance module. They also incorporated minor bug fixes to existing components, likely improving the overall accuracy and reliability of the Duckling NLP library. Finally, the user bumped the project version.
react-nativefacebookreactduckling
reboarchers/reboarchers.github.io
Feb 2015 - Feb 2016
Contributions:48 commits, 39 pushes, 1 branch in 1 year
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.