// AI Automation & Agentic Systems Engineer
Building systems that think, decide & act autonomously
I design Agentic AI, multi-agent pipelines, LLM-powered automation, and RAG architectures that connect AI to real engineering workflows — from Jira ticket routing and CI/CD orchestration to Graph RAG knowledge systems.
// who I am
Engineer at the intersection of AI systems and real-world automation
I'm an AI Systems Engineer based out of India, currently building multi-agent automation at EPAM Systems. My work sits at the edge of LLM orchestration and practical engineering — I care deeply about systems that don't just generate text, but actually do things.
My journey started in full-stack engineering, moved through GenAI product development at Infosys, and has now evolved into designing agentic workflows with Human-in-the-Loop controls, Temporal orchestration, and LLM-driven decision engines.
I believe the most interesting AI work happens when intelligent systems interact with messy real-world infrastructure — Jira tickets, Jenkins pipelines, CI/CD systems, and production databases. That's where I operate.
Outside of work, I explore Graph RAG architectures, build open-source AI projects, and experiment with local models using Ollama and LangGraph.
// career
From full-stack engineering to LLM-powered agentic systems
// capabilities
From LLM orchestration to cloud deployments
// builds
Personal experiments at the frontier of AI, agents, and full-stack engineering
Real-time entity extraction using spaCy feeds a dynamic Neo4j knowledge graph for relationship-aware Graph RAG querying. Integrates LangChain Text2SQL agents for natural language queries against auto-generated SQLite databases from uploaded documents. Uses Ollama with FAISS for semantic document chunk search and summarization — combining graph traversal with vector similarity in a single pipeline.
Multi-agent system using LangGraph and a custom MCP server to intelligently route user queries to specialized agents based on intent. Powered by a local Llama 3.2 model running fully on-device, demonstrating production-grade agentic frameworks without cloud LLM dependency. Personalizes conversation flow by routing inquiries to the most contextually appropriate agent.
End-to-end event management platform for creating, viewing, and participating in live events. Angular performance optimized with ChangeDetection strategy and lazy-loading, reducing initial load time by 70%. NgRx and RxJS handle state management, Redis caching handles traffic spikes.
Full-stack GenAI application generating context-aware text using GPT-2 models hosted via Hugging Face. Custom prompt and tokenizer pipelines for creative content. React frontend with controls for style, tone, and length tuning. Node.js backend handles API integration, session caching, and generation state.
// background
Academic foundation in engineering
// credentials
Verified expertise across AI, cloud, and graph platforms