I am an AI Systems Architect focused on designing, deploying, and operating production-grade multi-agent LLM backends. I build autonomous systems that run continuously on live Linux VPS infrastructure, with ownership spanning architecture, implementation, testing, deployment, and operations.
I have designed and shipped seven autonomous production systems, including multi-model LLM orchestration, machine-learning trading agents, live trading bots, and a remote job acquisition engine. My systems emphasize reliability, real-time processing, model fallback, cost tracking, daemon supervision, and actionable operational dashboards.
My primary language is Python, and I work extensively with FastAPI, gRPC, Redis, Celery, asyncio, REST APIs, WebSockets, and SQLite. I have hands-on experience integrating major AI providers including Claude, GPT, Grok, DeepSeek, Groq, and Gemini, as well as local inference with Ollama.
I specialize in multi-agent orchestration, model routing, cross-validation pipelines, RAG, prompt engineering, online learning, and production automation. I am comfortable building systems that coordinate multiple processes, providers, queues, data stores, and external APIs in real time.
Alongside my technical work, I bring operations and people-management experience from dispensary management and high-volume guest services. I am accustomed to compliance, escalation handling, staff supervision, inventory operations, and delivering reliable service in fast-paced environments.