Ten selectedcase studies.
Big Data
Big Data Analytics Pipeline — pyspark, hive & spark sql at ~2m records
Big Data
Text Classification on Spark — distributed mllib over 13,000 features
Working together?
Here's the shape of it.
I'm open to full-time AI/ML and senior engineering roles in the UK, and I take a small number of freelance projects alongside — audits, builds and getting models into production. No agency overhead, no slide decks. Code, measurements and honest answers.