I am an Applied AI Engineer and Backend Developer bridging the gap between scalable microservices and intelligent LLM workflows. I build reliable, production-grade AI systems focused on high throughput, cost optimization (like context caching), and measurable business impact.
Current Stack & Focus:
- AI/ML: Gemini 2.5, LangGraph, RAG (FAISS, Azure AI Search), LoRA/QLoRA, LLM-as-a-Judge (DeepEval, RAGAS)
- Backend: Java 21, Spring Boot, Python, FastAPI
- Cloud/Ops: Azure, AWS, Docker, Grafana
📝 Check out my technical writing on Medium where I discuss LLM orchestration, system architecture, and scaling enterprise AI.






