Headline

Gen AI Engineer @ Photon | CSE Graduate (Networking) | Agentic AI · RAG Pipelines · Prompt Engineering · LLM Integration | LangChain · LangGraph · Azure · GCP | AI/ML & Cybersecurity

About

I build AI agents that don't just respond — they collaborate, delegate, and act. As a Gen AI Engineer at Photon's PHTNAI product team, I work at the intersection of agentic orchestration, RAG systems, and multi-cloud LLM deployment. I've engineered agent-to-agent communication flows from scratch following Google's A2A standards, cut orchestration setup time from minutes to seconds, and built RAG pipelines that ground LLM responses across GPT, Gemini, Claude, and Llama — all in a production enterprise environment. What I actually do day-to-day: design and ship agentic pipelines using LangChain and LangGraph, optimize retrieval systems with FAISS, integrate LLM usage analytics for cost governance, and deploy containerized AI services on Azure Kubernetes Service across Azure and GCP. My background in Computer Networking (B.Tech, SRM IST — 9.37 GPA) gives me an edge most AI engineers don't have: I understand the infrastructure layer, not just the model layer. That means I build systems that are intelligent and production-ready. I'm currently open to full-time AI Engineer roles where I can keep building things that matter. 📩 Let's connect or drop me a message — always happy to talk AI, agents, or what we're each building.

Location

Chennai

Work experience

GEN AI Intern at Photon, Jul 2025 - Present · 11 mos, Chennai, Tamil Nadu, India, - Engineered agent-to-agent (A2A) communication flows from scratch in compliance with Google's A2A protocol standards, enabling autonomous inter-agent task delegation across Photon's enterprise agentic orchestration platform. - Architected reusable, configurable agent pipelines using LangChain and LangGraph, reducing agentic orchestration setup time from minutes to seconds for enterprise use case deployment. - Built and optimized RAG pipelines using FAISS vector databases to enable accurate document-grounded LLM responses across GPT, Gemini, Claude, and Llama (via Ollama), supporting multi-model enterprise workflows. - Designed and integrated LLM usage analytics into the PHTNAI platform — tracking token consumption, model spend, per-user history, and project-level usage across Azure OpenAI and GCP Vertex AI — enabling real-time cost governance for enterprise AI operations. - Deployed and managed containerized AI microservices on Azure Kubernetes Service (AKS), ensuring production-grade scalability and reliability across hybrid Azure and GCP cloud environments. - Applied advanced prompt and context engineering techniques to improve LLM response quality across diverse tasks; developed internal POCs and demoed directly to team leads and senior stakeholders.

Education

Bachelor's degree, Computer Science, SRM IST Chennai

11th and 12th Std, Kendriya Vidyalaya (KV)