AI Runtime Architect for ML Model Execution

Hewlett Packard Co.; Spring, Northern (TX, KY); Hybrid; USD 131,000 - 205,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Disability insurance

Life insurance

Job summary

Hewlett Packard Co. in Houston seeks an AI Runtime / ML Model Systems Engineer to develop runtime abstractions and model placement across heterogeneous compute resources.

You will design, develop, install, and maintain state-of-the-art software for the company and enable faster delivery of tools for engineers. The role requires strong AI runtime expertise, experience with ONNX, TensorRT, OpenVINO, and edge AI deployment, plus hands-on coding in C++, Python, and distributed systems.

Qualifications

• Experience with AI runtime architectures and model deployment across heterogeneous compute resources.
• Proven ability to design, develop, install and maintain complex software systems.
• Strong programming in C++ and Python with practical systems experience.

Responsibilities

• Build runtime abstraction frameworks and model placement policies.
• Develop xPU routing logic and optimize inference execution.
• Supervise external vendors, review tests, and provide technical guidance.

Skills

AI runtime expertise

Edge AI deployment

NPU scheduling

C++

Python

Distributed systems

Software development

Software engineering

Education

Four-year or graduate degree in CS/IT/SE

Tools

ONNX

TensorRT

OpenVINO

Docker

Kubernetes

AWS

Microsoft Azure

Job description

Hewlett Packard Co. in Houston seeks an AI Runtime / ML Model Systems Engineer to develop runtime abstractions and model placement across heterogeneous compute resources.

You will design, develop, install, and maintain state-of-the-art software for the company and enable faster delivery of tools for engineers. The role requires strong AI runtime expertise, experience with ONNX, TensorRT, OpenVINO, and edge AI deployment, plus hands-on coding in C++, Python, and distributed systems.