I build AI systems that are designed for production—not just demonstrations.

My work sits at the intersection of AI engineering, software architecture, and product thinking. I enjoy designing systems that are reliable, observable, and maintainable, whether that means orchestrating multi-agent workflows, building retrieval pipelines, or creating developer platforms powered by large language models.

I'm particularly interested in turning cutting-edge AI research into practical software that solves real business problems.

I'm an AI Engineer and Full-Stack Software Developer focused on building intelligent systems that bridge research and real-world applications. My work spans multi-agent architectures, LLM-powered platforms, retrieval-augmented generation (RAG), and developer tooling, with an emphasis on reliability, observability, and scalability.

Over the past three years, I've worked on enterprise fintech systems while independently designing and building AI products—from autonomous research agents and AutoML platforms to developer productivity tools. I enjoy taking ideas from architecture and experimentation to production-ready software that people can actually use.

Beyond writing code, I'm passionate about system design, product thinking, and creating software that remains maintainable as it grows. I believe the best AI products are built by combining solid engineering principles with a deep understanding of user problems.

These are representative systems that demonstrate how I approach AI engineering—from problem framing and architecture to deployment and evaluation. Each project reflects a different aspect of building production-ready AI solutions.

Technologies I use to design, build, deploy, and scale production-grade software and AI systems.

"Building reliable AI systems, one iteration at a time."