Pandari G

About

GenAI/LLM engineer with production deployments in both fintech and retail: built an AI-powered mortgage document analysis/automated underwriting pipeline at Fannie Mae (OCR + custom LLM) cutting underwriting review from 3–4 hours to under an hour with privacy-by-design controls. Also helped build Sephora’s GenAI product advisory bot using LangChain-orchestrated RAG (Azure GPT-4, Azure AI Search, MySQL HeatWave vector search), focusing on grounding, evaluation, and compliance-aware architecture choices.

Experience

Education

Key Strengths

• Built and deployed an AI-powered mortgage document analysis/automated underwriting system reducing review time from 3–4 hours to under 1 hour
• Production-grade security for sensitive financial/PII data (anonymization, private VPC subnets, data minimization)
• Strong orchestration experience across data/ML/LLM stacks (Airflow, LangChain, Argo CD)
• Designed RAG-based conversational product advisor with grounded recommendations (Azure ChatGPT + Azure AI Search + MySQL HeatWave vector search)
• Systematic evaluation approach for LLM workflows using KPIs, automated tests, RAGAS/LangChain eval, and human-in-the-loop feedback
• Improved classification of ambiguous financial transactions via semantic grounding with retrieved labeled examples injected into prompts
• Pragmatic architecture decisions balancing latency, compliance, and operational overhead (chose MySQL HeatWave over Pinecone to meet InfoSec constraints)