A lot of my work sits at the line between a clever demo and something that survives real traffic, monitoring, and edge cases. If you want, I can share how I approach shipping GenAI in production, or we can start elsewhere.
About
I am an AI Engineer focused on building production-grade Generative AI systems, including LLM-powered applications, AI agents, and RAG-based architectures.
I previously worked at Tazapay, where I built and deployed production GenAI systems and backend services using Python and Go. My work included designing AI agents and retrieval-augmented pipelines aimed at real-world business workflows, with a focus on reliability, evaluation, and scalability.
Before that, I worked as a Data Science Intern at Publicis Sapient, where I built machine learning models and data-driven solutions for business use cases.
Outside of internships, I built SyllabusPal, a production RAG-based AI application that helps students interactively understand and navigate academic syllabi using LLMs and retrieval systems. This project reflects my interest in applied AI systems that combine retrieval, reasoning, and user-facing product design.
My core interests lie in Agentic AI systems, RAG pipelines, LLM evaluation, and building production-ready AI infrastructure that bridges research and real-world deployment.
I am currently exploring full-time opportunities in AI Engineering roles where I can contribute to building scalable and reliable AI systems.
