I'm a software engineer based in China. Much of my work sits close to quantum measurement and control: representing chip topology, reasoning about calibration workflows, and turning research concepts into software that engineers can inspect and use.

I also build and study AI agents. I'm most interested in agents as dependable systems—not just demos—with explicit boundaries, observable behavior, stable failure semantics, tests, and interfaces that remain useful in real workflows.

• 🤝 Contributing upstream to Hermes Agent across scheduling, persistent goals, provider compatibility, messaging, and reliability.
• 🧪 Building the OpenAI Agents SDK Learning Lab as a practical path from a first agent to a bounded, observable terminal application.
• 🌱 Learning quantum error correction, surface codes, and lattice surgery in public through Learn QEC.
• 🧭 Exploring geometry-first representations of quantum hardware with QArray.

• Start with a reproducible problem and make the failure mode explicit.
• Keep changes reviewable, then validate them at the real platform or provider boundary.
• Treat tests, observability, and documentation as part of the product—not cleanup work.
• Prefer small, dependable tools over abstractions that are flexible only on paper.

Ask me about quantum chip topology, QEC learning, dependable agent systems, or developer tooling. If something I build is useful—or could be better—the simplest way to reach me is through the relevant repository or here as @M1racleShih.