Hi, I’m Simon Zhou.
I am a Machine Learning Engineer focused on speech AI, NLP systems, and edge-device model deployment. My recent work has centered on keyword spotting, low-power edge AI, model performance optimization, and automated workflows for training, evaluation, and data simulation.
Beyond speech algorithms and resource-constrained models, I am also interested in large language models, agent workflows, AI-assisted programming, machine learning visualization, developer tools, frontend/backend technologies, and software frameworks. I like understanding technology as a complete system: how models, data, toolchains, interfaces, deployment, and human workflows shape the final experience.
What I Work On ¶
- Speech AI and edge models: keyword spotting, speaker verification, sound event detection, model optimization, and deployment constraints
- NLP and LLMs: text classification, knowledge retrieval, dialogue systems, LLM applications, and agent workflows
- AI-assisted development: coding agents, automation tools, developer workflows, and new ways of building software
- Visualization and tooling: ML visualization, audio analysis tools, frontend/backend technologies, and productivity tools
Selected Work ¶
- AudioLens: a VS Code extension for audio inspection and spectrogram analysis, built for speech, audio, and ML engineers
- AI-assisted programming articles: notes on Codex, Claude Code, Gemini CLI, and agent-based coding workflows
- Machine learning visualization: articles that explain ML concepts through visual and interactive examples
Personal Side ¶
Outside of work, I enjoy music, games, and running. I also spend time following science, especially how AI is starting to change the way scientific research is done. I like understanding how different systems work and how their parts connect.
This blog is where I keep technical notes, tool experiments, learning records, and occasional personal observations.
Contact ¶
Mail: [email protected]
Github: @simzhou
X: @simzhouyh
LinkedIn: @yihua-zhou