Senior ML Platform Engineer: GPU Hosting & MLOps

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

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Generous time off

Job summary

HP, Inc. in the United States is seeking a Senior Machine Learning Platform Engineer to build the infrastructure and workflows that move models from development to production. You will host LLM inference on GPU infrastructure and shape the platform around model serving and deployment automation.

Collaborate with security and cloud teams to deliver scalable, observable hosting with IaC and robust pipelines across AWS and Azure, with potential on‑prem integration as needed.

Qualifications

• Hands-on experience hosting LLM inference on GPU infrastructure in production.
• Experience building a model-serving platform with runtimes, endpoints, scaling and tooling.
• Strong Python software engineering for services and automation.
• Delivery across AWS and Azure with IaC tooling.
• Kubernetes or equivalent hosting platform experience.
• ML deployment pipelines with versioned artifacts, CI/CD, promotion and rollback.
• Familiarity with LLM agent patterns and end-to-end tracing.
• Ability to collaborate across model development, application, platform, and security teams.

Responsibilities

• Design and build hosting for custom ML/AI models across AWS and Azure with GPU-backed inference.
• Package models into reproducible serving workloads and select suitable patterns.
• Provision and configure Kubernetes clusters and hosting infra including IAM, networking, observability.
• Develop IaC and deployment automation for consistent provisioning and promotion.
• Build MLOps workflows for model registration, versioning, validation, release, rollback.
• Connect training to deployment via automated pipelines and quality gates.
• Partner with teams on agent workflows, orchestration, state handling, and fault tolerance.
• Establish production monitoring for health, latency, throughput, and cost.

Skills

LLM inference hosting

Python

CI/CD

MLOps

Distributed systems

GPU infrastructure

Tools

Terraform

Kubernetes

AWS

Azure

SageMaker

Job description

HP, Inc. in the United States is seeking a Senior Machine Learning Platform Engineer to build the infrastructure and workflows that move models from development to production. You will host LLM inference on GPU infrastructure and shape the platform around model serving and deployment automation.

Collaborate with security and cloud teams to deliver scalable, observable hosting with IaC and robust pipelines across AWS and Azure, with potential on‑prem integration as needed.