At a glance
Steven J. Hubbard is an LLM and AI engineer and Solutions Architect with about 18 months of production LLM work in QA, code review and documentation. He uses tool and function calling, retrieval-augmented generation over client documentation, and structured prompt evaluation, with Claude Code and ChatGPT as daily engineering methods. He also builds the agent tooling: custom agent skills, purpose-built subagents and MCP integrations. He is available for remote contract and full-time work across the United States.
What I deliver
LLM integrationTool and function calling, retrieval-augmented generation (RAG) over client documentation, and structured prompt evaluation.
AI-assisted deliveryAI-assisted QA, code review and documentation embedded in real sprint cycles, with measurable results rather than demos.
Agent systemsClaude Code and ChatGPT as daily engineering methods: custom agent skills, 17 purpose-built subagents, MCP integrations with Gmail, Google Drive, Google Calendar and a Markdown knowledge base, and scheduled agent pipelines with automated verification gates.
Internal toolingInternal tools built with Retool and Python, and the automation around them.