Backend Engineer specializing in AI-powered systems and multi-agent architectures. I build production LLM applications with RAG, semantic caching, and scalable infrastructure.

🤖 40-80% LLM cost reduction via semantic caching (pgvector)
🚀 Multi-agent platforms handling 1000+ concurrent conversations
⚡ <200ms response latency with intelligent caching
💰 99.7% infrastructure cost reduction through cloud automation

Enterprise-grade SaaS deploying autonomous chatbots across Facebook, Instagram & WhatsApp.

Bun Hono PostgreSQL pgvector Redis BullMQ OpenRouter

• RAG-Powered Responses — Knowledge retrieval with pgvector embeddings
• Semantic Caching — 40-80% LLM cost reduction via similarity search
• Multi-Agent Engine — Independent bots with context, lead extraction, handoff
• Background Processing — BullMQ workers for async message handling

Resume optimization with NLP pipelines and multi-model AI architecture.

Python FastAPI spaCy OpenRouter MongoDB

• Multi-Model AI — OpenRouter + Gemini fallback with auto-failover
• NLP Pipeline — Entity extraction, skill detection, keyword analysis
• 95%+ ATS Scoring — Job description matching with STAR methodology

Knowledge retrieval chatbot with lead qualification automation.

Next.js Google Genkit Gemini TypeScript

Scalable retail management system with clean architecture.

Go Gin PostgreSQL GORM Flutter

Specializations: RAG Systems • Semantic Caching • Multi-Agent Architectures • LLM Integration • Vector Databases • Background Processing

• 🚀 Go + Python AI Stack — Go (Golang) for high-performance backend, Python for agentic AI intelligence
• 🤖 Google Agent Development Kit (ADK) — Building multi-agent systems with Google's agent framework
• 🔄 Multi-Agent Collaboration — Agents delegating to specialized sub-agents
• 🛠️ Tool-Using Agents — LLMs executing code and calling external APIs
• 🧠 Long-Term Memory — Persistent memory across conversation sessions