Data Engineer
Core
Build and maintain LLM-assisted web extraction workflows to collect, structure, store, enrich, and clean data from public web sources for a B2B event intelligence platform.
Role type
Data Engineer (Web Data & Automation)
Builds
Web data pipelines and LLM-assisted extraction workflows
Domain
B2B Event Intelligence / Web Data Automation
Deliverable
production ML models
Required skills
Python, web scraping, API integration, browser automation, database management, data cleaning and validation, LLM API usage, prompt engineering
Preferred skills
Experience with event data domains, taxonomy mapping
Technologies
Python, Requests, BeautifulSoup, Playwright, Selenium, Scrapy, Postgres, MySQL, MongoDB, Supabase, BigQuery, LLM APIs
Responsibilities
Build and maintain web data collection pipelines for public sources; Develop LLM-assisted extraction workflows; Use APIs, scraping tools, and browser automation; Store extracted data in clean formats; Enrich and standardise raw data; Clean, validate, deduplicate, and QA collected data; Debug failed jobs and parsing issues; Document workflows and extraction logic
Seniority
Mid-level, hands-on IC
