Principal Machine Learning Infrastructure Lead

CloudScale AI is looking for an extraordinary Principal ML Infra Lead to scale our model serving infrastructure across multi-cloud GPU clusters.

What You Will Do:
• Build inference runtimes optimized for sub-10ms token generation.
• Orchestrate automated batching and dynamic GPU scheduling.
• Partner with research scientists to deploy frontier generative models.

Requirements:
• Track record building production ML platforms at scale.
• Strong background in C++, Python, CUDA, and distributed scheduling algorithms.