Email 
LinkedIn 
Homepage 
GitHub 
Codeberg About Me
Core maintainer and lead architect of Juno (Java Unified Neural Orchestration) — an Apache 2.0, pure-Java framework for distributed LLM inference on the JVM. I work on coordinator/worker serving, GPU paths (CUDA / ROCm via Panama FFI), and OpenAI-compatible APIs so Java teams can evaluate on-prem LLM inference without a Python sidecar.
I live in the Houston area, work at Luxoft USA, and have demoed Juno at a HOSS Heights meetup. Happy to talk JVM systems, open source, and local inference.