HP
Senior Machine Learning Platform Engineer — Model Hosting & MLOps
$147K–$231K
Spring, Texas, United States of America +1 · Senior · Full-time · Posted Oct 6, 2026
- Location
- Spring, Texas, United States of America
Tlaquepaque, Jalisco, Mexico - Visa sponsorship
-
About the job
Builds and operates the infrastructure, serving workflows, and MLOps pipelines that move custom ML and AI models into secure, reliable production use across cloud and potentially on-premises environments.
What you'll do
- Design and operate GPU-backed model hosting and inference services across AWS and Azure, including Kubernetes or managed-service deployments.
- Build infrastructure-as-code, deployment automation, and MLOps workflows for model versioning, validation, release, rollback, and monitoring.
- Partner with application teams on agent workflows and production operations, including tracing, incident response, capacity, reliability, and cost.
What they ask for
- Production experience hosting LLM inference on GPU infrastructure.
- Experience building model-serving platforms and ML deployment pipelines with versioned artifacts, automated validation, CI/CD, promotion, and rollback.
- Strong software engineering skills, especially Python; experience with production services and automation.
- Hands-on ML infrastructure delivery across AWS and Azure, infrastructure as code, and Kubernetes or another production container hosting platform.
Nice to have
- Advanced GPU inference optimization or serving compute-intensive custom models.
- Experience with managed ML platforms, hybrid or on-premises hosting, model registries, or shared ML platform capabilities.
Pay
$147,050 to $230,850 USD annually — base salary
Tools
Python, AWS, Azure, Terraform, Kubernetes, AWS SageMaker, EKS, Azure Machine Learning
AI focus
Hosts custom ML and AI models, especially GPU-backed LLM inference; builds MLOps pipelines and helps design agent workflows using hosted models.
Model-written summary · the original posting is authoritative