Aryan Sivanandan

I’m an AI Engineer with experience building RAG systems, agentic pipelines, and full-stack AI products, and I’m an IEEE published researcher in ML-enhanced trading strategies. I’m hands on with FastAPI, vector search, LLM orchestration, and cloud-native development—focused on turning models into reliable, shipped applications.

In my Applied AI Consulting internship, I architected an end-to-end agentic interview automation system using LangGraph and LangChain with multimodal input via OpenAI Whisper, delivering sub-5s response latency and reducing recruiter manual screening time by 65%. I’ve also built end-to-end ML pipelines with TensorFlow and scikit-learn, and I’m currently developing an AI Second Brain RAG system (hybrid retrieval + reranking) with Next.js and a FastAPI backend.