Data & Analytics Solution Architect with 9 years at Siemens. Building governed AI foundations, semantic layers, and production-ready data products — documented, reproducible, and designed for scale.
Every repo here is a delivery narrative, not a demo. Architecture decisions, governance patterns, baseline-to-model flows, and the boundaries where manual work stops and automation starts. Built for hiring managers who want to read code — and for engineers who want to understand why the code was written.
Governance-first semantic layer + LLM chatbot for quotation analysis. Guardrails live in dbt transforms, not prompt engineering. Cortex masks sensitive data by design.
Baseline-to-model delivery flow with rolling-origin validation. Stakeholders audit the Excel baseline before the gradient boosting model is even trained. No data leakage, no overfit.
Product knowledge bot for HVAC specification questions. FAISS + Gemini embeddings with latency and accuracy metrics tracked. Built as production-ready MVP with clear roadmap.
Active experiments and utility scripts — smaller tools, data processing pipelines, automation helpers, and exploratory work that feeds into larger delivery patterns.
Academic research paper written during MBA studies.
Read paper →