hetvi patel

About

Backend/data engineer who built a production analytics data service (Python/FastAPI on AWS/Postgres with PySpark ETL) handling millions of records per day and drove major latency improvements (10–15s to <2s) via indexing, Redis caching, and shifting aggregations into ETL. Also shipped an LLM-based natural-language-to-SQL assistant end-to-end with strong guardrails (schema restrictions, read-only validation, RBAC, masking) and designed a multi-step agent workflow with verification and fallback logic.

Experience

Education

Key Strengths

• Built and operated a Python/FastAPI analytics backend on AWS/PostgreSQL processing millions of records daily
• Diagnosed and improved slow API/database performance using logs + EXPLAIN ANALYZE, indexing, query optimization, caching (Redis), and moving aggregations into ETL (10–15s down to <2s)
• End-to-end delivery of LLM-powered natural-language-to-SQL assistant (API design, pipelines, deployment, monitoring)
• Implemented AI safety/security guardrails: schema-restricted access, read-only query validation, row/join/time limits, RBAC, and sensitive data masking
• Designed multi-step LLM workflow/agent with planning vs execution vs verification, retries/fallbacks, and clarification/stop conditions
• Production Python maintainability practices: typed interfaces (type hints/Pydantic), async + background jobs, pinned dependencies (Poetry), unit/integration tests, observability (logging/monitoring/alerts)