Carthi P https://carthi-portfolio.pages.dev/ 2026-08-31T18:29:19.281273+00:00 Shrinking a PyTorch Model's Memory Footprint with ONNX https://carthi-portfolio.pages.dev/articles/onnx-inference-footprint/ 2026-08-31T00:00:00+00:00 A walkthrough of exporting PyTorch models to ONNX for deployment — what actually gets smaller, what doesn't, and the export gotchas worth knowing before you ship. What Actually Breaks in a Production RAG Pipeline https://carthi-portfolio.pages.dev/articles/production-rag-lessons/ 2026-03-22T00:00:00+00:00 Retrieval quality, not generation quality, is where enterprise RAG systems fail. Notes from building ingestion, embedding and vector search for enterprise document corpora. Designing a PySpark Pipeline That Survives Schema Drift https://carthi-portfolio.pages.dev/articles/pyspark-schema-drift/ 2025-11-18T00:00:00+00:00 Third-party data changes shape without telling you. Notes on building ingestion that fails loudly at the boundary instead of silently three tables downstream.