class SaiSivaSrinivas:
def __init__(self):
self.name = "Sai Siva Srinivas Munduru"
self.role = ["AI Engineer", "Full Stack Developer", "Java Backend Developer"]
self.focus = [
"Production-grade LLM applications & RAG pipelines",
"Hybrid search • Vector DBs • RAGAS-driven evaluation",
"Real-time SaaS platforms with WebSocket & Redis",
"Distributed Java microservices with Kafka & Spring Boot"
]
def current_stack(self):
return {
"ai_ml" : ["LangChain", "LlamaIndex", "LangGraph", "CrewAI", "AutoGen", "RAGAS"],
"backend" : ["FastAPI", "Spring Boot", "Node.js", "Express.js"],
"frontend": ["Next.js", "React", "TypeScript", "Tailwind CSS", "ShadCN UI"],
"infra" : ["Docker", "AWS", "Redis", "Kafka", "Pinecone", "PostgreSQL"],
}
def fun_fact(self):
return "My RAG pipeline hit faithfulness ≥ 0.91 before I hit my morning coffee ☕"
Hybrid search RAG backend (vector + BM25) with ~38% improvement in context recall Redis caching cut latency from ~1.2 s → 180 ms (85% reduction) RAGAS scores: faithfulness ≥ 0.91 · answer relevancy ≥ 0.88 Deployed on AWS EC2 with Docker Compose · JWT-ready · streaming responses
Real-time SaaS supporting 50+ concurrent users · live updates in < 50 ms PostgreSQL schema optimisation → query times reduced by ~45% RBAC (Owner/Editor/Viewer) · CI/CD via GitHub Actions · < 5 min build-to-deploy 🌐 Live Demo
Distributed rate limiter handling 10,000+ req/s with < 2 ms overhead Token bucket + sliding-window · circuit-breaker cut downstream failures by ~60% 85%+ JUnit 5 + Mockito test coverage · Kafka violation streaming · Docker Compose
| 🏅 Certification | 🏢 Issuer | 📅 Year |
|---|---|---|
| IBM Generative AI Engineering Specialization | IBM | 2026 |
| Oracle Cloud Infrastructure — Generative AI Professional | Oracle | 2025 |
| Google Cloud Digital Leader | Google Cloud | 2026 |
