Built RAG over 30M+ vectors, delivering lightning-fast, production-grade GenAI systems. Expert in LLM integration and backend engineering. Ex-Morgan Stanley & Grab. Toptal freelancer helping teams scale AI and infrastructure with confidence.
I specialize in building Retrieval-Augmented Generation (RAG) systems that scale — including real-world deployments over 30M+ vectors across diverse unstructured data sources. With a strong backend engineering background (ex-Morgan Stanley, Grab; Toptal freelancer), I’ve built and productionized GenAI pipelines using leading vector DBs and LLMs.
Whether you're working with PDFs, support tickets, product manuals, or raw documents — I can help you design, build, and optimize end-to-end RAG workflows that are fast, accurate, and ready for scale.
Let’s solve your RAG challenges, from architecture to implementation.
