Anmol Garg

At EXL Analytics, I work at the intersection of AI and data engineering for FinTech. I designed a multi-agent root-cause-analysis platform on Databricks — LangGraph and Claude over a Milvus vector store — that lets analysts ask plain-English questions of reconciliation data and cuts root-cause analysis from hours to under five minutes. I also build production RAG pipelines over 1 TB of financial data and serve Llama 3.3 70B with vLLM at 128 concurrent requests.

I came to AI from the data side, and I build like it. At Jio Platforms, I architected the real-time ingestion pipeline for Jio AirFiber — 1.2 billion records an hour through Kafka, Spark, and Delta Lake — and a metadata-driven data platform for Jio Financial Services that cut ad-hoc pipeline development time by 90%. That experience left me with a conviction I bring to every AI system I build: it is only as reliable as the data platform underneath it.

I hold a B.Tech in Electronics Engineering and am a Databricks Certified Data Engineer Professional and a Microsoft-certified Fabric Data Engineer Associate. Outside work, I’m a competitive programmer — All-India Rank 1,122 on LeetCode (top 0.08%) and Expert on Codeforces (peak 1617).