Python Data & AI Engineer — Web Scraping / Document Extraction / Databricks

Elinext is recruiting a Python Data & AI Engineer to join a project focused on automated search, extraction, structuring, validation, and delivery of technical asset data from publicly available Internet sources. The role involves designing and implementing a solution that automatically collects and structures technical information from manufacturer websites, digital product catalogs, online directories, portals, databases, engineering publications, technical datasheets, and product-related documents. The extracted data will be normalized, validated, and provided in standardized CSV files for integration into an existing Enterprise Asset Management (EAM) structure.

Key responsibilities include analyzing public data sources, designing the target architecture for data acquisition and extraction, developing components for data collection, parsing, extraction, mapping, and normalization, processing structured and unstructured information from websites, APIs, PDFs, tables, and documents, applying AI/LLM-based approaches to extract and normalize technical characteristics, developing rules for data validation, duplicate detection, and quality control, transforming collected information into structured asset, manufacturer, product, and type objects, preparing standardized CSV outputs with full source traceability, building validation workflows and supporting functionality in Databricks, implementing completeness, plausibility, and reliability checks, supporting pilot implementation for selected asset classes, measuring extraction quality, identifying opportunities for optimization and scaling, and preparing technical, operational, architecture, and handover documentation.

The ideal candidate will have strong Python development experience, proficiency with Pandas and PySpark, hands‑on experience with Databricks and Delta Lake, experience building data pipelines and data transformation workflows, a solid understanding of data normalization, schema mapping, and validation, experience working with REST APIs and file‑based data sources, experience processing structured and unstructured documents (PDF, datasheet, table extraction), source and metadata management, error handling and monitoring of data processing runs, and experience with Large Language Models / Generative AI and NLP-based information extraction. Fluency in English is required; German is a plus.

The position is located in the EU region and may involve remote or hybrid work arrangements, but specific format details are not provided. The role is full‑time and requires a senior‑level skill set, though exact experience level is not specified. Salary details are not disclosed.