About this role

As an AI Runtime / ML Model Systems Engineer, you will develop runtime abstraction layers and intelligent model placement systems across diverse compute resources. You will be instrumental in building cutting-edge software applications and services that empower other developers to deliver faster with modern tools. This role is key to optimizing inference execution and ensuring efficient AI model deployment.

What we are looking for

6

Build runtime abstraction frameworks
Implement model placement policies
Develop xPU routing logic
Optimize inference execution
Expertise in ONNX, TensorRT, OpenVINO
Experience with NPU/GPU scheduling and Edge AI deployment

Skills mentioned

9

PythonC++JavaJavaScriptSQLReactAzureDockerKubernetes