Francisco Javier Arceo
Forward Deployed Engineer @Baseten, Maintains the vLLM Agentic API Project
Francisco Javier Arceo is a Forward Deployed Engineer at Baseten and an open-source leader with more than a decade of experience across AI, software engineering, and fintech, including roles at Red Hat, Affirm, and Goldman Sachs. His background spans machine learning, data infrastructure, and production software systems. He maintains the vLLM Agentic API project, which builds infrastructure that connects coding harnesses and other agentic applications to open-weight models built on top of stateful APIs, tool execution, and streaming.
Open Source Agentic Inference: Unlocking the Harness with vLLM
Coding agents are turning inference into a continuous workload. A single developer task can trigger dozens of model calls, tool executions, and an expanding context window.