At Edra Labs LLP, I architect backend services for a production RAG platform, covering data ingestion, chunking, retrieval, and low-latency APIs across industrial datasets. I also developed distributed pipelines for conversational memory and for processing data from web pages, PDFs, images, and videos.
I built scalable API and ingestion infrastructure at Edra Labs, including services for 20+ datasets and processing across 40+ workers. Previously, at Xpressbees Logistics, I owned and scaled an Auto-IVR backend handling 5000+ calls per day and integrated AWS SQS and Lambda for asynchronous workflows.

