Philipp Ladner

Data & AI systems

• End-to-end data pipelines: acquisition, validation, transformation, storage (sql-based) and delivery
• Retrieval-augmented generation (RAG) for large document collections with source grounding
• LLM-based validation, rule-based QA, and agent-style automation workflows

Data quality & reliability

• Automated anomaly detection, completeness checks, and data lineage concepts
• Monitoring and alerting for data drift, broken pipelines, and SLA breaches
• Designing quality checks that balance rigor with operational feasibility

Document intelligence

• Large-scale parsing and structuring of unstructured documents (PDFs, reports, filings)
• Embeddings, vector search, and knowledge-aware retrieval
• Converting narrative-heavy sources into analytics-ready datasets

Decision support & analytics

• Statistical & mathematical modelling, simulation, and sensitivity analysis
• Building interactive dashboards.
• User-friendly, auto-refreshing visualizations tied to live or batch data sources