Data Pipeline Engineer — Shopify Scraper + LLM Parser

What We're Building XyberDreams turns Shopify product pages into immersive 3D commerce experiences. To do that, we need a pipeline that takes a Shopify product URL and outputs structured product data + brand metadata, ready for our frontend to render. You will own this pipeline end-to-end. --- What You'll Build A system that takes a Shopify product URL as input and returns structured JSON as output. The pipeline handles: - Extracting product info (title, price, images, variants, options) - Detecting and extracting content sections (FAQ, sizing, shipping, returns, care, materials) - Capturing brand signals (logo, colors, fonts, navigation) - Using an LLM to classify, parse, summarize, and generate the final structured config Input: Shopify product URL Output: Clean, validated JSON ready for downstream rendering --- How You Build It Is Up To You We don't dictate tools or architecture. Pick what gets the job done well - Playwright, Puppeteer, Scrapy, Python, Node, OpenAI, Claude, whatever fits. We care about the output, not the process. --- Who You Are - You've built scrapers or data pipelines on real-world websites before - You've worked with LLM APIs and structured outputs (JSON schema, validation, retries) - You ship working code fast — bias toward action, not over-engineering - You can start within a few days of being hired - You're responsive and can do daily check-ins --- Compensation $1,000 base + up to $500 bonus based on hitting success metrics. Details shared during interview. --- How to Apply Submit through LinkedIn with: 1. A link to a relevant project (GitHub, portfolio, or a brief description of past scraper / data pipeline / LLM work) 1. One sentence on why this project interests you If we're a fit, we'll book a 15-minute call within 24 hours to talk through how you'd approach this.