Hari Chandini Dabbiru

I'm building Python-based data scraping, extraction, and AI workflows at Optum Healthcare, improving downstream AI data quality by 25% and reducing manual processing effort by 30%.

I develop FastAPI microservices with Docker and build LangChain and FAISS retrieval solutions that improved retrieval precision by 32% in compliance-driven workflows. I also use Apify, OpenRouter, and MLflow to strengthen extraction accuracy and deployment traceability.

Previously at State Farm, I led web scraping and ingestion workflows using Python, Azure DevOps, LangChain, FastAPI, and Azure Kubernetes Service. My work improved pipeline reliability by 22%, reduced retrieval response times by 35%, and increased fraud-pattern detection accuracy by 28%.

At Fluent Grid, I automated more than 25 ETL workflows with Apache Beam and Apache Airflow, built Dockerized Flask APIs, and managed data extraction on Google Cloud Platform and BigQuery. I bring hands-on experience turning high-volume operational data into dependable pipelines and analytics-ready datasets.