Dhananjaya KC

At Prodapt Solutions, I build end-to-end data migration pipelines that move enterprise data from Oracle to Azure Data Lake using Azure Data Factory and Azure Databricks.

I develop scalable ETL workflows with Python, PySpark, Spark SQL, and Medallion Architecture across Bronze, Silver, and Gold layers. I create curated, analytics-ready datasets, validate and reconcile data, and optimize distributed processing for large-scale workloads.

I also designed an AI-powered knowledge retrieval system using RAG architecture, FAISS, LangChain, Ollama, vector databases, and local LLMs. The system supports semantic search over technical documents through document ingestion, embeddings, vector indexing, and grounded response generation.

I enjoy building reliable, high-performance data platforms that turn complex source data into useful analytics and business insights.