GPU-Accelerated LLM Serving Platform Engineer

This role involves designing, building, and operating a production-grade, GPU-accelerated LLM serving platform that powers multiple AI products at enterprise scale. The position requires managing Kubernetes clusters with NVIDIA GPU nodes, optimizing multi-GPU inference, and implementing autoscaling policies to balance cost and latency. The engineer will also maintain infrastructure as code, manage observability stacks, and ensure high performance for large language model deployments.