Design, build, and maintain high-traffic production LLM serving systems. Optimize throughput, latency, and cost for open-source language models by tuning inference engines and GPU execution stacks. Troubleshoot and improve inference performance, and collaborate to scale efficient, reliable inference infrastructure.

Design and implement core features across the stack (Python, TypeScript, Rust); make product-focused engineering decisions; build scalable, well-tested, documented production software; prioritize engineering investments; collaborate in a remote synchronous team; contribute to consumer apps, developer platforms, infrastructure, or AI research.