Chetana Reddy Yellareddy

About

Backend/AI engineer who built and scaled an internal AMD semiconductor manufacturing microservice platform (SMR), reworking a synchronous lot-request workflow into an event-driven RabbitMQ/Celery/FastAPI pipeline. Diagnosed and fixed peak-load reliability issues using deep observability and Kubernetes autoscaling, cutting notification latency back to sub-second and reducing duplicates via idempotency/DLQs. Also shipped an LLM-powered natural-language search with schema-constrained JSON outputs and guardrails, plus a plan-execute-verify Jira bug-resolution agent that can propose fixes and raise PRs under restricted permissions.

Experience

Education

Key Strengths

• Re-architected synchronous workflow into async event-driven pipeline (RabbitMQ/Celery/FastAPI)
• Production performance tuning using observability (Prometheus/Grafana/RabbitMQ metrics/Flower)
• Scaled high-throughput notification system (1400 req/hr spikes; backlog 25k) to sub-1s avg latency and P95 ~2–3s
• Reliability engineering: idempotency keys, DLQs, controlled retries to reduce duplicate notifications (<0.2%)
• Designed secure LLM-to-structured-query layer with schema validation, guardrails, and fallbacks
• Built plan-execute-verify agent workflow with policy-driven retries/escalation and restricted tool permissions
• Maintainable Python practices: layered architecture, typed/validated boundaries (Pydantic), consistent error contracts, strong tooling/testing