Siemens

• Deployed Selenium crawlers and AWS pipelines to automate macroeconomic data collection; optimized PySpark workflows, improving resource utilization by 30% and reducing processing time by 45%.
• Cleaned and migrated COPA data with pandas and delivered CPD reports to business teams, supporting performance analysis and decision-making.
• Developed scripts to scrape, structure, and ingest million-scale business documents into a RAG knowledge base supporting Siemens’ in-house LLM and grounded, domain-specific responses.