I build production LLM infrastructure, evaluation systems, retrieval and agent workflows, and the operational machinery that makes AI products reliable, observable, and economically sane.
I am currently a Senior Software Engineer, AI at Klarity. I also research language-model agents, social simulations, and programmable subjects. This site is my home on the web: a compact index of work, research, code, writing, and ways to reach me.
I am focused on systems that let teams ship AI features without turning every release into a model gamble: multi-provider execution, eval gates, replay-based migration, cost analytics, tracing, and incident workflows.
Research-wise, I am interested in LLM agents as experimental subjects: how they remember, coordinate, imitate, drift, and respond to simulated social environments.
| pdfvuer | A PDF viewer component for Vue.js built on Mozilla's PDF.js. | |
| Manas | Python framework and experiments for LLM-powered applications and agent workflows. | |
| More | Other projects and contributions live on GitHub. |
Preprint, 2025.
arXiv preprint arXiv:2505.09081, 2025.