Rushikesh Shaharao

I’m an AI Engineer with 3+ years of experience building production-grade AI systems, agentic workflows, and enterprise GenAI applications. I focus on turning cutting-edge AI capabilities into reliable systems that can run at scale.

Currently at SingleStore, I build AI-powered platforms that automate complex engineering workflows using LLMs, LangGraph, and observability systems. My recent work includes building autonomous AI agents, developing AI infrastructure for large-scale workflows, and implementing LLM guardrails.

I’ve worked across agentic AI, RAG systems, LangChain/LangGraph development, and LLM evaluation. I also apply AI security and safety practices—helping ensure models and agents behave safely while supporting enterprise knowledge retrieval and intelligent automation.

Previously, I contributed to AI security platforms (including automated red-teaming frameworks) and NLP research using transformer-based models. I enjoy solving problems at the intersection of AI engineering, systems design, and product impact, especially when reliability, safety, and observability are core requirements.