Satwika Boppudi

About

Backend/AI engineer in healthcare/insurance (mentions Cigna) who has shipped production systems spanning high-reliability APIs, async job architectures (Celery), and LLM/RAG features. Built an LLM document assistant with Terraform-managed AWS infra, semantic search retrieval, and strict permissioning/audit logs, and designed an automated prior-authorization workflow with human-in-the-loop escalation and compliance-driven thresholds.

Experience

Education

Key Strengths

• Debugged and resolved peak-hour API timeouts by moving slow third-party calls to Celery background jobs
• Careful rollout strategy (kept old endpoint running in parallel; gradual cutover with monitoring)
• Improved operational visibility by adding Flower for live Celery job monitoring
• Built and owned end-to-end LLM document assistant (AWS infra via Terraform, RAG pipeline, auth/permission checks, CI/CD)
• Improved LLM retrieval relevance by switching from keyword search to embedding-based semantic search and adding relevance thresholds to prevent hallucinations
• Designed reliable agent/workflow for prior authorization with retries, escalation to manual review, and compliance sign-off on thresholds
• Data-driven production tuning of automation thresholds ($500 to $2000) based on ops feedback and observed escalation rates
• Relational data modeling and query optimization (indexes + denormalization) with integrity preserved via PostgreSQL triggers and validation scripts
• Production readiness practices: structured logging with request/user context, CloudWatch + PagerDuty alerting, staging integration tests