I build agent systems, then measure whether they actually work.

AI engineer, backend by training, Go by default. Concretely, three things: I build agent systems (MCP servers, knowledge bases with PostgreSQL and pgvector, retrieval that is actually evaluated); I put models into production (serving architecture chosen against a real CPU or GPU budget, deployment to cloud GPUs and Jetson edge devices); and I instrument all of it with OpenTelemetry, Prometheus and Grafana so the numbers are real.

M.S. in Computer Science, National Chung Hsing University. Two open-source research projects on ML serving — one benchmarks three architectures under CPU limits, the other implements the second study's batching proxy in Go — and a blog on what the benchmarks leave out. Open to opportunities.