I build production AI platforms and backend infrastructure, with a focus on LLM serving, GPU workloads, Kubernetes, observability, reliability, and inference performance.
I have over a decade of experience building backend systems, leading engineering teams, and delivering production platforms.
- LLM serving and inference infrastructure
- Kubernetes-based AI platforms
- Performance, capacity planning, and observability for GPU workloads
- Distributed systems and reliable backend services
I'm particularly interested in Senior and Staff engineering roles focused on AI infrastructure, ML systems, distributed systems, and developer platforms.