Available for opportunities
The infrastructure you don’t see. The reliability you feel.
I’m Ruthvik Garlapati, an SRE and AIOps engineer. I build resilient cloud systems and AI-powered automation that keep production moving at any scale.
KubernetesTerraformPythonAWSObservabilityLLM engineering
Selected work
Two projects built around safety-critical reliability, and two that put AI to work on incident response.
Autonomous vehicles · SRE · NVIDIA NIM
Fault-tolerant AV perception: YOLOv8n primary with an LLM fallback on NVIDIA NIM, validated by NeMo Guardrails. An SRE watchdog redirects vehicle control on SLO breach.
SLO-driven failover for a safety-critical perception path, with no human driver as fallback.
EKS · AIOps · AWS Bedrock
Production microservices on EKS with Terraform, ArgoCD, Prometheus and Grafana, plus an AWS Bedrock and Lambda AIOps assistant for natural-language queries of live metrics.
Ask live production metrics a question in plain English, no dashboard digging.
Claude API · RAG · ServiceNow
Claude API with RAG over postmortem docs. A Terraform-managed Lambda webhook delivers AI runbooks into ServiceNow incidents when a Prometheus alert fires.
Runbook creation cut from 3 hours to under 10 minutes.
MCP · Claude · ServiceNow
Production MCP server connecting Claude to ServiceNow, with 9 tools for incident triage, knowledge-base search and CMDB dependency mapping.
87% P1/P2 priority accuracy on a 35-case eval suite.
The journey
Software Engineer · Contract
DevOps Engineer · Intern
Graduate TA · Cloud Computing & RDBMS
Software Quality Engineer
Software Engineer · Intern
Education & certifications
MS, Information Systems · GPA 3.9
BTech, Computer Science
Linux Foundation · CKA
NVIDIA Certified Associate
Anthropic
Skills & expertise
Let’s build something
Have a challenge worth solving? I’d love to hear about it.