[Agentic AI] AI Runtime / ML Model Systems Engineer
Core
Develop runtime abstraction layers and intelligent model placement systems across heterogeneous compute resources to optimize inference execution.
Role type
Senior IC ML Model Systems Engineer
Builds
Runtime frameworks, model placement policies, and xPU routing logic for AI inference
Domain
AI Infrastructure / Heterogeneous Compute
Deliverable
production ML models
Required skills
ONNX, TensorRT, OpenVINO, NPU/GPU scheduling, Edge AI deployment, C++, Python, Kubernetes, Docker, Microservices, DevOps, API design, Software Architecture
Preferred skills
Full Stack Development, React.js, Java, JavaScript, SQL, Agile Methodology, AWS, Microsoft Azure
Technologies
ONNX, TensorRT, OpenVINO, Kubernetes, Docker, AWS, Azure, C++, Python, Java, React.js, SQL
Responsibilities
Build runtime abstraction frameworks; Implement model placement policies; Develop xPU routing logic; Optimize inference execution; Lead software development projects and platforms; Automate software deployment; Design solutions to manage software products and data; Contribute to technology strategy and engineering roadmaps; Supervise external engineering vendors
Seniority
Senior, hands-on IC
