Data Engineer Scraping, ETL, LLM Pipelines

Що робити

• Build new datasets from scratch: structured scraping of sources like accelerators and Form D filings, parsing content with LLMs, and storing it cleanly in Supabase with well-defined schemas.
• Stand up eval frameworks for our LLM pipeline so we can benchmark and swap different models across our various LLM calls.
• Help design more scalable pipeline architecture, likely leveraging GCP-based services.
• What we're looking for
• 4+ years building data pipelines, backend services, and automated data processing systems, with a core focus on web scraping and ETL.