I am a Data Science and Mathematics developer focused on building trustworthy AI architectures, semantic search pipelines, and robust data engineering solutions. I specialize in turning massive, unstructured datasets into clean, deterministic knowledge graphs and actionable systems.
🌍 Explore my full portfolio, resume, and blog at lcpizani.github.io
- Languages: Python, SQL, R, C++, Java, TypeScript
- AI & Machine Learning: PyTorch, Scikit-Learn, Hugging Face, SBERT Embeddings, Named Entity Recognition (NER), Prompt engineering.
- Data Engineering & Graph: Neo4j, ChromaDB, PostgreSQL, Large-scale Hierarchical Clustering
- Tools & Analytics: Git, Docker, Tableau, AWS
- Trust-First AI Architecture: Building intelligent agents that favor deterministic, high-stakes computation and validation over raw generative outputs.
- Knowledge Graphs & Ontologies: Developing entity-linking pipelines and structural clustering models to canonicalize hundreds of thousands of capability phrases.
- Data Quality & Validation: Crafting automated schemas to ensure the reliability and structure of synthetic data generations.
- Website: lcpizani.github.io
- LinkedIn: Lucas Pizani