Python Engineer for Automated Technical Reference Matching

We’re looking for a senior Python engineer to improve an existing system that matches industrial equipment records with the correct manufacturer documentation. The system receives equipment details such as brand, model, type, and configuration, then needs to identify the most appropriate technical reference, obtain the source document, and verify that it actually applies to that specific equipment. A working implementation already exists. This is primarily an optimization and reliability project rather than a new build. You’ll review the current pipeline, existing test results, known edge cases, and prior experiments before recommending changes. The difficult cases are usually older equipment, poorly indexed manufacturer websites, archived documents, inconsistent model naming, and manuals hosted outside the OEM’s main site. The system must also know when not to return a result if the evidence isn’t strong enough. Experience that would be useful: Python automation Web data acquisition Document matching / classification PDF processing Crawling and archive retrieval Entity or product-model resolution Ranking/scoring systems Search APIs Performance profiling and telemetry