Swati Swati

About

AI software engineer with experience spanning LLM/RAG production systems and regulated fintech infrastructure. Built an end-to-end natural-language-to-SQL analytics assistant (Weaviate + GPT-4 + Supabase) shipped as an API with 92% accuracy and major time savings for non-technical users, and also owned demand-forecasting and CI/CD/containerization improvements for a Bank of America core banking deployment at Infosys.

Experience

Education

Key Strengths

• Built and shipped end-to-end RAG NLQ system (Weaviate + GPT-4 + Supabase) as a production API
• Delivered 92% production accuracy for NLQ answers and reduced analytics question time by ~85% for non-technical users
• Turned around sparse/noisy time-series baseline (negative R) by redesigning pipeline and engineering 15+ forecasting features
• Productionized XGBoost in Node.js via ONNX export and JS feature parity with Python
• Pragmatic, risk-aware modernization in regulated banking (incremental containerization, CI/CD first, rollback/stability focus)
• Designed scalable core-banking transaction processing prioritizing consistency/ACID; validated via load tests, failure sims, and reconciliation
• Hands-on incident triage and root-cause analysis; fixed CI/CD image build/permissions issue causing timeouts and transaction failures