HP
[Agentic AI] AI Runtime / ML Model Systems Engineer
$131K–$205K
Spring, Texas, United States of America +1 · Full-time · Posted Sep 30, 2026
- Location
- Spring, Texas, United States of America
Austin, Texas, United States of America - Experience
- Typically 7–10 years; preferably in software design and development, software architecture, programming languages, or a related field.
- Education
- Four-year or graduate degree in Computer Science, Information Technology, Software Engineering, or a related discipline, or commensurate work experience or demonstrated competence.
About the job
Develops AI runtime abstraction and model-placement systems across heterogeneous compute resources, optimizing inference and enabling other engineers to build and deploy software.
What you'll do
- Build runtime abstraction frameworks and implement model-placement policies and xPU routing logic.
- Optimize inference execution and develop software deployment standards and automation.
- Lead software projects and platforms; contribute to engineering strategy and roadmaps, and oversee external vendors’ testing work.
What they ask for
- ONNX, TensorRT, and OpenVINO.
- NPU/GPU scheduling.
- Edge AI deployment.
Nice to have
- Strong AI runtime expertise.
Pay
$130,700 to $205,200 USD annually (base salary)
Tools
ONNX, TensorRT, OpenVINO, NPU/GPU, C++, Docker (Software), Kubernetes, Python (Programming Language)
AI focus
Builds AI runtime abstraction, model placement, xPU routing, and inference optimization systems.
Model-written summary · the original posting is authoritative