Lead ML Inference Systems Engineer (Remote)

Runpod is hiring a ML Systems Engineer, Inference, to lead end-to-end LLM serving performance and cost optimization. You’ll measure, diagnose, and improve throughput, latency, and efficiency across models and hardware generations in production. You’ll own tooling, runtimes, and configurations, collaborating with product and infra teams to shape inference offerings while staying current with the open-source ecosystem and benchmarking best practices. J-18808-Ljbffr