Dynamic Deployment Engineer for Machine Learning Inference Clusters

Become a Deployment Engineer focused on revolutionizing AI inference capabilities. Enhance deployment reliability and operational efficiency within sophisticated AI compute infrastructures.

In this essential role, you will lead the deployment of AI inference replicas and optimize software rollout across various global datacenters. Utilizing your systems engineering and operational skills, you will develop advanced telemetry solutions and automated pipelines, playing a key part in capacity management. Your work will bridge technical requirements with internal teams to ensure seamless operations.

Key Responsibilities: • Deploy and manage AI inference software across multiple datacenters • Operate in rapidly growing heterogeneous environments • Optimize capacity allocation and replica positioning • Enhance telemetry and observability frameworks • Build automated deployment pipelines for agile operations

Requirements: • 2-5 years in on-prem compute infrastructure...