multi-agent
View on GitHub ↗Local multi-agent orchestration framework with sandboxed tool execution. Agents collaborate on tasks using locally-hosted LLMs — no cloud dependency.
I'm a software consultant with a background in statistical physics, materials simulation, and deep learning. My research applied neural networks to inverse design problems in 2D materials — finding patterns where classical methods couldn't scale. Now I build practical ML systems: pipelines, multi-agent frameworks, and production-grade models.
Local multi-agent orchestration framework with sandboxed tool execution. Agents collaborate on tasks using locally-hosted LLMs — no cloud dependency.
End-to-end ML pipeline for ad targeting: feature engineering, model training, evaluation, and serving — structured for production deployment.
Deep learning for inverse design of 2D kirigami metamaterials. Neural networks predict cut patterns that achieve target mechanical properties — replacing expensive FEM sweeps.