Senior ML Platform Engineer: Model Hosting & MLOps

Hewlett Packard Co.; Spring, Northern (TX, KY); Hybrid; USD 147,000 - 231,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Time off & holidays

Job summary

Hewlett Packard Co. is seeking a Senior Machine Learning Platform Engineer to design and operate hosting for custom ML models across AWS and Azure.

You will package models, implement reproducible serving workloads, and build scalable MLOps pipelines for model registration, validation, and release. The role requires hands-on GPU-based LLM inference experience, strong Python engineering, and expertise in Kubernetes-based hosting, CI/CD, and cloud platforms.

Qualifications

• Hands-on experience hosting LLM inference on GPU in production.
• Experience building the surrounding model-serving platform for custom models and end-to-end pipelines.
• Strong software engineering skills with Python for services and automation.
• Experience provisioning and operating Kubernetes-based hosting platforms.
• Familiarity with ML deployment pipelines, versioned artifacts, and CI/CD practices.

Responsibilities

• Design and build hosting for custom ML models across AWS and Azure.
• Package models into reproducible serving workloads and choose deployment patterns.
• Provision Kubernetes clusters and related hosting infra with observability and IAM.
• Build MLOps workflows for model registration, versioning, validation, release, and rollback.
• Collaborate with application teams on agent workflows and hosting decisions.

Skills

LLM hosting GPU

Python

MLOps

CI/CD

Cloud platforms

Tools

Kubernetes

Terraform

Docker

AWS

Azure

Git

Job description

Hewlett Packard Co. is seeking a Senior Machine Learning Platform Engineer to design and operate hosting for custom ML models across AWS and Azure.

You will package models, implement reproducible serving workloads, and build scalable MLOps pipelines for model registration, validation, and release. The role requires hands-on GPU-based LLM inference experience, strong Python engineering, and expertise in Kubernetes-based hosting, CI/CD, and cloud platforms.