AI Infrastructure Engineer
I build the infrastructure AI agents run on — and I've written the frameworks myself: agent runtimes in Go (agent-go) and Rust (harness-rs, on crates.io), a memory + RAG + knowledge-graph engine (cortexdb), and an LLM evaluation framework (eval-go). I turn LLM demos into agents that run unattended in production.
I help teams turn LLM demos into production AI agents — building agent systems, RAG and knowledge-graph retrieval, and MCP integrations that connect agents to your real tools, APIs, and databases. Primarily in Go and Rust.
Yes — that's the core of the work. I take an LLM prototype and turn it into a reliable system that runs unattended inside your real environment, with evals, guardrails, documentation, and a clear deployment path.
Yes. I'm comfortable joining an existing codebase and integrating agent, RAG, and MCP capabilities into systems you already run — not only greenfield projects.
Yes. I build custom MCP servers that let agents take real actions — connecting internal tools, APIs, and databases so an agent can do useful work, not just chat.
Yes — open to a full-time remote role or contract. I'm remote-first and async-friendly, based in Chengdu (UTC+8), and work with US and EU teams through clear written communication and documentation. Reach me at ll_faw@hotmail.com.
harness-rs (a Rust agent framework on crates.io), agent-go (a Go AI agent SDK), cortexdb (a pure-Go AI memory + knowledge-graph engine with vector/hybrid search and GraphRAG), eval-go (a native-Go LLM/agent evaluation framework with judge-alignment), and a suite of MCP servers for Swagger/OpenAPI, web search, and SQLite. I build the tooling agents are made of, not just apps that call an LLM.
I take an LLM from “demo” to running unattended inside your systems.