Data SciencemidhybridcontractUtilities, Insurance, and TelecommunicationsPythonScrapyBeautifulSoupSeleniumSQLSnowflakeAirflowNLPposted 10 Jul
Unlock apply linkApply links and the original listing are a Pro feature — £4.99/mo or £25 once.
Data Scientist – Data Engineering \& Web Scraping (Debt Tracing) – Utilities Sector
* Rate:
£500/day (Inside IR35)
* Contract:
3 months rolling
* Location:
Primarily remote, with occasional travel to Nottingham or London
* Sector:
Utilities
Role:
* Build and maintain web scraping pipelines to gather structured and unstructured data for customer tracing purposes
* Identify and locate customers in arrears using data engineering techniques across multiple public and internal data sources
* Design entity resolution/fuzzy matching logic to link historic account records to newly sourced contact data (address, employer, phone, social)
* Build scalable ETL pipelines to ingest, clean, and structure scraped data into existing data warehouse/CRM systems
* Apply NLP/text extraction techniques to pull relevant details from unstructured web sources
* Work closely with Collections/Recoveries teams to prioritise and validate traced leads
* Ensure all data collection and processing is compliant with UK GDPR and FCA guidance on debt collection conduct
Skills required:
* Strong Python (Scrapy, BeautifulSoup, Selenium/Playwright)
* SQL and data warehousing experience (Snowflake/BigQuery/Redshift or similar)
* Record linkage/fuzzy matching (fuzzywuzzy, recordlinkage, dedupe or similar)
* ETL/orchestration tools (Airflow, dbt)
* NLP/text mining exposure
* Experience in financial services, utilities, or collections/recoveries a strong plus
* Understanding of GDPR/data compliance in a regulated environment