Senior ML Platform Engineer - GPU Inference & MLOps

HP; Spring (TX); On-site; USD 147,000 - 231,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Disability insurance

Employee assistance program

Flexible spending account

Life insurance

Generous time off

Job summary

HP is seeking a Senior Machine Learning Platform Engineer to build infrastructure and workflows that move custom models from development to production. You will host LLMs on GPU infrastructure, shape cloud-hosted model serving, and create repeatable MLOps pipelines for release, monitoring, and cost control.

You will design hosting across AWS and Azure, implement IaC, and collaborate with application teams on agent workflows, data handling, and security.

Qualifications

• Hands-on experience hosting LLM inference on GPU infrastructure in production.
• Experience building model-serving platforms with inference runtimes, endpoints, scaling, and tooling.
• Strong Python software engineering skills for services and automation.
• Experience delivering ML workloads on AWS or Azure with IaC (Terraform or equivalent).
• Experience provisioning and maintaining Kubernetes for containerized inference workloads.
• Experience building ML deployment pipelines with versioning, validation, CI/CD, and rollback.

Responsibilities

• Design hosting for ML/AI models across AWS and Azure with GPU-backed LLM inference and real-time endpoints.
• Package models into reproducible serving workloads using containers or Kubernetes patterns.
• Provision and configure Kubernetes clusters, including IAM, networking, observability, and security.
• Develop IaC and deployment automation for repeatable provisioning and promotion of environments.
• Build MLOps workflows for model registration, versioning, validation, release, and rollback.
• Collaborate with teams on agent workflows, including tool integration and tracing.

Skills

LLM inference hosting

Python software engineering

Infrastructure as code

Kubernetes production hosting

AWS/Azure deployment

Tools

Terraform

Kubernetes

AWS

Azure

Job description

HP is seeking a Senior Machine Learning Platform Engineer to build infrastructure and workflows that move custom models from development to production. You will host LLMs on GPU infrastructure, shape cloud-hosted model serving, and create repeatable MLOps pipelines for release, monitoring, and cost control.

You will design hosting across AWS and Azure, implement IaC, and collaborate with application teams on agent workflows, data handling, and security.