Principal ML Ops Engineer — Remote AI Infra Leader

Jobgether in South Africa is seeking a Principal ML Ops Engineer to lead the design and operation of production-grade ML inference infrastructure powering large-scale AI applications. You will own model serving systems, GPU-powered infrastructure, deployment pipelines, and operational excellence.

Collaborating with infra, platform, and applied AI teams in a remote-first environment, you will shape engineering standards and build foundational systems from the ground up, driving cost efficiency