← Jobs

Data Integration Specialist for Manufacturer Data

Budget: $20.0 - $40.0 HOURLY / PART_TIME ⭐ 4.96 (12) United States

python, php, api-development, big-data

We are seeking a skilled freelancer to help integrate product data from manufacturers. The data arrives in various formats, including Excel spreadsheets with different layouts, EDI feeds, PDF spec sheets, and vendor websites. The ideal candidate will have experience in data integration and transformation, ensuring that all data is accurately and consistently formatted for our system. This project requires attention to detail and the ability to handle complex data sets. Design a repeatable ingestion workflow for manufacturer product data across multiple categories (appliances, lighting, paint, masonry, fixtures, etc.) Use AI/LLM tooling (e.g., Claude, GPT-4, or similar) to extract, classify, and map product attributes from unstructured and semi-structured sources into our defined schema Build field-mapping logic that handles inconsistent column names, units of measure, and attribute conventions across manufacturers Ingest structured feeds (Excel/CSV, EDI, vendor APIs) and normalize them into our SQL Server database Implement validation and QA checks: dedupe, catch bad units, flag missing required fields, and surface low-confidence AI mappings for human review Document the pipeline so our team can run and extend it for new manufacturers Work with our founder to prioritize manufacturers and refine the catalog schema as real-world data exposes gaps. Must-Have Qualifications Proven experience with large-scale data ingestion, ETL, or master data management (MDM) — show us a project where you took messy source data and produced a clean, structured result Hands-on experience using LLMs/AI for data extraction, classification, or entity mapping (prompt pipelines, structured output, confidence scoring, human-in-the-loop review) Strong SQL skills; comfortable working against SQL Server Proficiency in Python or C# for pipeline scripting Experience handling Excel/CSV at scale (pandas, EPPlus, ClosedXML, or similar) A methodical approach to data quality: you validate, you don't assume Nice to Have EDI experience (X12, EDIFACT) or experience consuming vendor product feeds/APIs Familiarity with product information management (PIM) systems or e-commerce catalog data Construction, building products, or home improvement industry exposure Azure experience (Azure Functions, Data Factory, Blob Storage) .NET / ASP.NET Core familiarity (our platform stack)
Open job