NLP Data Engineer

About the role

Data engineer building scalable NLP/LLM document processing pipelines with Python, Spark, Hugging Face and vector databases.

Requirements

• Strong Python
• NLP tokenization and text processing
• Spark and Spark SQL
• Vector databases
• 2-3 years in data engineering or NLP

What you'll do

• Build document ingestion pipelines
• OCR and parsing
• Chunking for LLM apps
• Vector DB pipelines

Where this was posted

• LinkedIn

  last seen 1h ago
  View on LinkedIn