AI Systems Engineer

I build production AI systems that ship and stay reliable, not demos. My work focuses on LLM agents, RAG systems, chatbot infrastructure, and reliability engineering for AI products that need to work in real-world conditions.

I am the solo engineer behind Project Maxima, a 24/7 production AI assistant with multi-model Claude routing, hybrid RAG over Qdrant, temporal knowledge memory, Langfuse observability, and live reliability evaluation. I design end-to-end systems that can handle messy inputs and continue working after launch.

I also built AETHER Genesis, an AI companion product with paying customers, and Axiom AI, a unified multi-provider LLM gateway. These projects reflect my ability to take AI ideas from architecture through implementation, deployment, and iteration.

My technical background includes Python, FastAPI, REST APIs, Telegram bot infrastructure, prompt engineering, multi-agent workflows, vector databases, knowledge graphs, and observability tooling. I also work with evaluation pipelines, cost and latency monitoring, and failure recovery to make AI systems dependable.

In my professional experience, I have supported healthcare operations, maintained high quality assurance standards, trained new agents, and led knowledge transfer work. I also worked as an IT network technician, where I strengthened my troubleshooting, infrastructure, and debugging skills.

I am open to full-time remote AI engineering roles where I can contribute to LLM agents, RAG systems, and production AI reliability. I bring a builder mindset, strong execution, and a focus on systems that perform consistently in production.