Karl Lorey
Founder at apistemic
Berlin, Germany
Summary
🤩
Rockstar🎓
Top SchoolKarl Lorey is a Berlin-based founder and builder with 11 years of experience turning data and machine learning into investable products and startups. He founded apistemic and its flagship product startupradar.co to enable AI-driven startup scouting, and previously co-founded a tech-focused €5M VC where he used scrapers and ML to surface early deals. Technically hands-on, Karl ships production scraping and ML pipelines (Python, scikit-learn, Scrapy) and prototyped an ML-driven HTML element detector in his open-source mlscraper project. He has repeatedly moved from research (encrypted DBs at KIT) to product, taking ideas through MVP to funding and handover as interim CTO. Known for pragmatic engineering—“using whatever gets the job done”—he blends data-driven product instincts with operator experience sourcing and monetizing hard-to-get datasets.
11 years of coding experience
6 years of employment as a software developer
Master’s Degree Computer Science, Master’s Degree Computer Science at Karlsruhe Institute of Technology (KIT)Bachelor’s Degree Computer Science, Bachelor’s Degree Computer Science at The Julius Maximilians University of Würzburg
English, French, German
Stackoverflow
1,576reputation
154kreached
26answers
3questions
php
top-5%
laravel
top-5%
Github Skills (21)
python10
scikit10
scikit-learn10
decision-tree10
laravel9
machine-learning9
php9
beautifulsoup8
webscraping8
scraper7
pandas7
crawler7
nested6
html6
phantomjs6
Programming languages (11)
Github contributions (5)
lorey/mlscraper
Jun 2020 - Jan 2023
🤖 Scrape data from HTML websites automatically by just providing examples
Role in this project:
ML Engineer
ML EngineerContributions:2 releases, 122 commits, 1 PR in 2 years 7 months
Contributions summary:Karl primarily focused on implementing machine-learning-based functionality within the mlscraper project. They added a prototype utilizing a decision tree classifier for element detection on websites, demonstrating an understanding of machine learning principles. The user's work included defining preprocessing steps and training a pipeline for classification tasks. Furthermore, they integrated and tested the model on a website, showcasing their ability to apply machine learning to a real-world scraping problem.
extraction-enginepythonscrapyscrapemachine-learning
germanitjobs/perfect-german-cv
Sep 2016 - Apr 2017
Contributions:12 commits, 9 pushes, 1 branch in 7 months
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.