Kevin Rodriguez

I build systems that are fast, clear, and maintainable. Currently at Cornell and working on agent orchestration and resource management.

Currently working on

Local Multi-Agent Loop

Two Qwen 27B agents sharing a pair of 3090s, working through a ~140-task plan to find, reproduce and fix bugs in open-source ML repos. The interesting part is everything around the model: a task tree so each step knows where it sits, short handoff notes when an agent stops, and a llama-server setup that keeps the prompt cache warm. The second agent bought about 20% more throughput.

agent runs: 294
of agent time: 89 h
tokens generated: 8.9M
prompt-cache reuse: 7% → 97%

Read the report →See a run ↗