Platform LLM Infrastructure Engineer

Sumeru Solutions

Job Location:

Seattle, OR - USA

Monthly Salary: Not Disclosed

Posted on: 2 hours ago

Vacancies: 1 Vacancy

Job Summary

The Platform LLM Infrastructure Engineer operates at the intersection of capacity planning GPU capacity optimization quota management model lifecycle management and production reliability This role is critical in ensuring scalable efficient and resilient infrastructure for large language model LLM platforms

Key Responsibilities
Manage shared GPU resources across regions including handling LLM capacity requests and optimizing utilization
Deploy and migrate production models while reclaiming capacity from systems that are no longer in use
Drive stakeholder coordination and enable datadriven capacity planning decisions
Validate performance through stress testing to ensure production readiness and reliability
Design and implement automation solutions to streamline infrastructure operations and reduce manual effort
Contribute to evolving AIdriven operational capabilities including intelligent agents and copilots for platform efficiency

Technical Skills
Core MustHave
Azure OpenAI Azure AI services
Automation using Power Platform Copilot Required
Azure Active Directory AAD
Azure Storage Azure SQL Azure Data Explorer
NET Core C Python
REST APIs
Azure DevOps

Good to Have
Azure AI Foundry
Agentic AI concepts and implementations autonomous agents orchestration frameworks AIdriven workflows

Nice to Have Emerging Skills
Experience in building AIpowered automation copilots or intelligent workflow systems
Exposure to LLMbased platform optimization and AIdriven infrastructure management

The Platform LLM Infrastructure Engineer operates at the intersection of capacity planning GPU capacity optimization quota management model lifecycle management and production reliability This role is critical in ensuring scalable efficient and resilient infrastructure for large language model ...