Principal Full-Stack AI Engineer
I engineer LLM-powered products end-to-end — RAG pipelines, voice AI and prompt systems on top of scalable React, Next.js, Node.js and Python architecture. Code that ships, scales, and feels alive.
I own the full lifecycle — from LLM architecture to production UI — turning AI, RAG pipelines and full-stack systems into products that actually ship, scale and delight the people using them.
Tools I Build With.
Six years of turning ideas into software people actually rely on. I move across the full stack — React and Next.js up front, Django and FastAPI holding the line in back — then push further into the AI layer: RAG pipelines, voice agents and fine-tuned LLaMA / OpenAI models built to perform outside a demo. Docker, AWS and GCP carry it into production, and I stay close to it long after launch.
React & Next.js
Architecting fast, accessible interfaces — from marketing sites to complex dashboards — with modern React patterns.
Django & FastAPI
Secure, scalable REST APIs and services built for real traffic — clean data models, clear contracts.
LLMs & RAG
Prompt systems, retrieval pipelines and fine-tuned models that stay on-brand and hallucinate less.
Conversational Agents
Speech-to-text and text-to-speech pipelines for voice assistants that actually sound natural.
Storage & Retrieval
Schema design and vector search tuned for products that need to scale past a prototype.
Ship & Operate
Dockerized deployments on AWS and GCP — owning everything from architecture to on-call.