Rohith kollu

About

Backend/platform engineer who has built and scaled production Java/Spring Boot + Kafka services on AWS/Kubernetes (1M+ msgs/day) and led reliability/performance fixes that restored SLAs (25–30% latency improvement; 99.9% uptime). Also shipped an AI customer-support chatbot end-to-end using retrieval + guardrails and rigorous evaluation/observability, improving resolution time 40% and satisfaction 25%, with a strong plan/execute/verify approach to agentic workflow reliability.

Experience

Education

Key Strengths

• Built and operated AWS/Kubernetes Java Spring Boot + Kafka services at 1M+ messages/day with strict latency/uptime SLAs
• Diagnosed and fixed slow-burn latency degradation via indexing/query optimization, connection pool contention fixes, and Kafka consumer batching (25–30% latency reduction; stabilized consumer lag; met 99.9% uptime)
• Production-minded incident response and change management: stabilize-first prioritization, reversible changes, canary/feature-flag rollouts, and explicit success metrics
• End-to-end ownership of an AI customer support chatbot (backend, orchestration, retrieval, observability, deployment, iteration) delivering 40% faster resolution and 25% higher satisfaction
• Strong RAG/agent reliability approach: canonical knowledge schema, two-stage retrieval, confidence thresholds, anti-hallucination guardrails, and human escalation with structured context
• Designs reliable multi-step workflows with explicit plan/execute/verify separation, idempotency, retry budgets, loop detection, and audit trails