Remote job
AI Agentic Scraping Engineer
Job details
About this role
Role overview Build and maintain the data extraction layer that lets AI agents retrieve structured product information from online shops. You’ll expand coverage across marketplaces, retailers and brand stores, while using agent workflows to create and validate extractors and taking responsibility for the accuracy of their output.
Responsibilities - Create and maintain extractors for shop search, catalog and product pages. - Build agent workflows that draft extractors, test them on live pages and prepare changes for human review. - Monitor source changes with sample runs, schema checks and alerts, then repair extractors when results drift or break. - Standardize product records, including prices, currencies, variants, stock and seller details. - Coordinate with backend engineers on job reliability, retry behavior and the cost of processing pages.
Requirements - At least three years of production experience collecting website data at scale, using Python or TypeScript. - Regular hands-on use of AI coding agents, with practical understanding of their limitations. - Familiarity with HTTP, HTML, embedded JSON APIs and browser automation. - Experience testing and validating data quality as well as code. - Clear written English for pull requests, issue reports and incident notes.
Nice to have - Experience working with ecommerce data or major online marketplaces. - Experience building or using MCP servers or LLM tool-calling systems. - Background in product matching or entity resolution.