Jackson Lee
Engineering Manager, Professional Services at Civis Analytics
Greater Philadelphia United States
Summary
👤
Senior🎓
Top SchoolJackson Lee is an engineering manager and computational linguist with 12 years of experience building scalable data pipelines, identity resolution systems, and ML infrastructure in consultancy and platform settings. Currently leading Professional Services at Civis Analytics, he has doubled as a tech lead creating client-agnostic integrations and owning Python computing environments and Docker images that power company-wide workflows. His background as a linguistics PhD and contributor to core NLP tooling like NLTK informs a pragmatic approach to text processing, probabilistic PII resolution, and production ML. He’s delivered solutions across public-sector and commercial clients, balancing hands-on engineering with mentoring and sales engineering support. Notably, he led development of a widely reused person data standardization tool and maintains dozens of integrations between Civis Platform and major data sources. Based in the Greater Philadelphia area, he combines research-grade language expertise with strong delivery and platform-operational instincts.
12 years of coding experience
12 years of employment as a software developer
Master of Arts (M.A.) Linguistics, Master of Arts (M.A.) Linguistics at The University of ManchesterThe University of Hong Kong (HKU)Doctor of Philosophy (PhD) Linguistics, Doctor of Philosophy (PhD) Linguistics at University of Chicago
English, Chinese, Chinese, French, Spanish, German, Hakka, chaozhou, mauritian creole
Github Skills (5)
nltk10
machine-learning10
nlp10
python10
natural-language-processing10
Programming languages (8)
Github contributions (5)
nltk/nltk
Aug 2015 - Oct 2017
NLTK Source
Role in this project:
ML Engineer
ML EngineerContributions:10 commits, 3 PRs, 6 comments in 2 years 3 months
Contributions summary:Jackson's contributions primarily focus on enhancing the `nltk` library's functionality related to natural language processing. They made changes to the CHILDES corpus reader, improving how the system handles word stems and POS information. Furthermore, they implemented changes to the Perceptron tagger, allowing it to handle iterators for training data and optimizing its workflow, which is crucial for efficient training. The commits also include additions for test data downloads.
nltkpythonnlpnatural-language-processingmachine-learning
jacksonllee/wikipron
Oct 2020 - Oct 2020
Scraping grapheme-to-phoneme data from Wiktionary
Contributions:12 commits, 108 pushes, 68 branches in 6 days
graphemewiktionarycomputational-linguisticsg2pgrapheme-to-phoneme
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.