Skip to content

Systems & Projects

Architectural Case Studies & Technical Builds

Engineering write-ups detailing system architecture, data flow, engineering trade-offs, and production delivery.

  • data-pipelines
  • information-retrieval
  • machine-learning
  • nlp
  • pyspark
  • vector-search
featured

Pair-Programming Pipeline Engineer & Communications Lead

NLP & Vector Search: Extracting Knowledge from Historical Scientific Literature

Design and implementation of a two-phase NLP system combining PySpark-based text processing, sub-word TF-IDF classification, and dense vector embeddings to identify and retrieve species descriptions from historical scientific journals.

  • data-pipelines
  • pyspark
  • vector-search
  • nlp

· 9 min read

Read case study