I’m an AI engineer and full-stack developer who enjoys turning complex ideas into working products. Over the past few years, I’ve built conversational AI systems, LLM-based chatbots, voice automation tools, and backend services that power real businesses. I work across the stack, but my strength lies in designing and deploying practical AI solutions that people can actually use.
My experience includes building chatbots with LLaMA, GPT, and custom RAG pipelines, creating agent-based systems that reason across tools, and integrating NLP models into production workflows. I’ve also developed real-time voice AI platforms involving ASR, LLM reasoning, and TTS running over WebSockets, as well as telephony integrations with Twilio for automated calling and scheduling.
On the engineering side, I work comfortably with Python, FastAPI, Docker, Redis, PostgreSQL, and modern cloud environments. I like taking ownership of a feature from early prototype to production deployment, making sure it’s reliable, traceable, and easy for clients to use or extend.
I’ve also shipped a multilingual mobile app using Flutter and Riverpod, collaborated with cross-functional teams, and worked directly with clients to refine requirements and deliver features that match their goals. Clear communication matters to me, and I make it a point to keep clients updated, aligned, and confident throughout the project.
If you’re looking for someone who can help you design an AI feature, build it from scratch, or fix and scale an existing system, I can help. Whether it’s chatbot development, RAG pipelines, automation, voice AI, backend APIs, or productionizing ML ideas, I bring a mix of practical ML knowledge and solid engineering experience.
I prefer working with clients who want real results, not just experiments. If you have an idea you want to bring to life, need help improving an existing AI workflow, or want guidance on how AI can fit into your product, I’d be happy to work with you.