I’m a linguist and data scientist working at the intersection of linguistics and engineering. I build data infrastructure for conversation analytics: synthetic data generation systems, evaluation methodologies, and annotation tooling that enables research and development teams to build and test conversation analytics systems.

Most recently, I was a Language Data Scientist at AWS supporting Amazon Transcribe’s Contact Lens Applied Science Team. There, I built agentic annotation systems for trend detection ground truth annotations, developed evaluation systems for LLM-generated summaries, and created synthetic dialogue generation pipelines for multilingual customer service conversations.

I maintain mkdnflow.nvim, a Neovim plugin with 700+ stars for navigating markdown documents and markdown-based journals or wikis. I’m happiest when building, whether that’s tools, knowledge, solutions to problems, or objects meant to be beautiful, and I’m gratified by continually improving those things. I’m currently looking for my next role.