Jacob Perkins
Senior Software Engineer at Streamhacker Technologies
San Francisco, California, United States
Summary
👤
Senior🎓
Top SchoolJacob Perkins is a senior software engineer and entrepreneur with 16 years of experience building ML, NLP, information architecture, interaction design, and web-facing applications. Based in San Francisco, he currently serves as a Senior Software Engineer at DFINITY, applying scalable software engineering and cryptography-aware approaches to cutting-edge platforms. As a founder and CTO, he led Streamhacker Technologies and Fletch, delivering NLP-powered cybersecurity search engines and AI-enabled product pipelines across startups. An active open-source contributor, his NLP work on NLTK includes corpus readers, tagset mapping, and tooling upgrades, and he co-created the nltk-trainer to train classifiers with zero code. He holds MS and BS degrees in Computer Science from Washington University in St. Louis and has a proven track record of turning complex requirements into practical, auditable solutions in the San Francisco Bay Area.
16 years of coding experience
15 years of employment as a software developer
MS, BS, Computer Science, MS, BS, Computer Science at Washington University in St. Louis
English, Spanish
Stackoverflow
21reputation
446reached
1answer
0questions
Github Skills (12)
nltk10
machine-learning10
nlp10
python10
natural-language-processing10
classification10
algorithms7
netflix6
amazon-web-services6
hadoop6
elastic-map-reduce6
apache-pig6
Programming languages (3)
Github contributions (5)
japerk/nltk-trainer
Oct 2010 - Apr 2020
Train NLTK objects with zero code
Role in this project:
Back-end Developer
Back-end DeveloperContributions:189 commits, 2 PRs, 5 pushes in 9 years 7 months
Contributions summary:Jacob primarily worked on the `train_classifier.py` script, which is designed to train and evaluate NLTK classifiers. Their contributions involved the creation of corpus reader components and feature extraction options. The user also added the ability to select and use different classification algorithms, including NaiveBayes and Maxent. Further work included updates to handle multiple classification tasks within a single process.
nlpzeromachine-learningnltknatural-language-processing
nltk/nltk
Apr 2011 - Apr 2015
NLTK Source
Role in this project:Back-end Developer
Back-end DeveloperContributions:6 commits, 1 PR, 2 comments in 4 years 1 month
Contributions summary:Jacob primarily contributed to the `nltk` repository by implementing and modifying corpus readers and related functionalities. Their work involved creating `TimitTaggedCorpusReader`, updating existing readers like `ConllCorpusReader` and `SwitchboardCorpusReader` to support tagset mapping and simplifying tag handling, and refactoring code to use `nltk.Tree` instead of `Tree`. The contributions demonstrate a focus on improving the corpus readers' capabilities, including handling of tagged data and integration with other NLTK components.
nlppythonmachine-learningnltknatural-language-processing
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.