Support machine learning model serving at Baseten through scalable infrastructure, performance standards, and dependable operational processes. Learn directly from users building AI products.
As a Cloud Platform Engineer, you will build systems that keep model deployment and operation scalable, reliable, and effective. Your work may include multi-cloud capacity management, B200 GPU inference, multi-node inference, and fractional H100 GPU serving. You will also automate deployments, monitor systems, and manage incidents while owning projects end to end.
Key Responsibilities
Maintain infrastructure supporting machine learning model operations
Optimize infrastructure performance and manage operational incidents
Automate deployments and relevant engineering processes
Own products and projects through specification and execution
Mentor junior team members and share organizational knowledge
Requirements
Experience maintaining scalable infrastructure
Extensive experience with Kubernetes
Experience with infrastructure-as-code tools
Experience with CI/CD tooling
Openness to learning machine learning without prior experience
Apply infrastructure engineering judgment to help Baseten operate advanced model-serving systems across evolving AI workloads.