Open to opportunities

Sanket Raj

@sanketraj1

Message

AI Engineer building cloud-native LLM systems—RAG, multi-agent orchestration, and Kubernetes-deployed backends.

India

Message

What I'm looking for

I’m looking to build production-grade LLM systems—RAG and multi-agent orchestration—with cloud-native deployment on Kubernetes, where reliability and end-to-end shipping matter and I can grow with SRE/platform teams.

I’m an AI Engineer with cloud infrastructure experience from a DevOps/LLM integration internship at InnoVent Solutions, plus independent work shipping end-to-end systems solo. I blend backend engineering (FastAPI, distributed systems) with cloud-native deployment (AWS, Docker, Kubernetes, CI/CD) to build reliable AI-powered services.

I’ve built multi-agent orchestration on the ReAct protocol, RAG pipelines (including a cloud RAG assistant covering 300+ cloud services), and Kubernetes-deployed backend services with automatic failure recovery. I also focus on reliability tooling—like GitOps-based alert ingestion with prompt-engineered root cause analysis and Helm rollback—so teams can trust agentic workflows in production.

Experience

Work history, roles, and key accomplishments

DevOps/LLM Integration Intern

InnoVent Solutions

Completed a DevOps/LLM integration internship at InnoVent Solutions, building cloud-infrastructure capabilities for LLM/RAG systems. Combined backend engineering with cloud-native deployment using FastAPI and Kubernetes on AWS with CI/CD.