Muhammad Irfan
Data Scientist
Punjab, Pakistan
Summary
👤
Senior🎓
Top SchoolMuhammad Irfan is a Lead AI Engineer with 12 years of experience building production-ready machine learning and NLP systems, currently leading AI efforts at JTech Solutions while freelancing as a data scientist on Upwork. He holds a Master’s in Artificial Intelligence from NUST and has a track record of shipping applied ML across startups and consulting engagements, from AI research to senior engineering roles. A specialist in Urdu NLP, he contributed Urdu language support to the widely used spaCy project—fixing ISO codes, adding tags, tests, and configuration—while also running the Urdu NLP resource blog. Colleagues know him for turning messy, multilingual datasets into reliable models and for bridging research, engineering, and localization to make models useful in underserved languages.
12 years of coding experience
5 years of employment as a software developer
ICS, Computer Science, A+, ICS, Computer Science, A+ at Soft Vision College of Information Technology, Bahawalpur.Metric, Science, A+, Metric, Science, A+ at Govt. Sadiq Dane Model High School Bahawalpur.Master’s Degree, Artificial Intelligence, Master’s Degree, Artificial Intelligence at National University of Sciences and Technology (NUST)Bachelor of Science (BS), Computer Science, Bachelor of Science (BS), Computer Science at Islamia University, Bahawalpur
English, Saraiki, Urdu, Punjabi
Stackoverflow
67reputation
13kreached
0answers
11questions
Github Skills (15)
nlp10
spacy10
python10
natural-language-processing10
tokenizer9
tokenize9
fork6
caching6
centos6
command-line-interface6
activerecord6
vagrant6
asterisk6
angularjs6
gcc6
Programming languages (12)
Github contributions (5)
explosion/spaCy
Jun 2018 - Apr 2020
💫 Industrial-strength Natural Language Processing (NLP) in Python
Role in this project:
Localization / Internationalization Specialist
Localization / Internationalization SpecialistContributions:6 commits, 7 PRs, 16 comments in 1 year 9 months
Contributions summary:Muhammad primarily contributed to the spaCy project by adding and fixing support for the Urdu language. They implemented Urdu language support, added tests, and modified configuration files. Furthermore, the user fixed the ISO code for Urdu and added missing tags, improving the NLP capabilities of spaCy for the Urdu language.
fairness-mlpythondata-preprocessinglanguage-processingtokenization
mirfan899/Urdu
Feb 2019 - Jan 2023
Collection of Urdu datasets for POS, NER, and NLP tasks
Contributions:61 commits, 57 pushes, 1 branch in 3 years 11 months
nlpposnerurdu-languagenlp-tasks
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.