Description

You will serve as the critical bridge between inference systems and the broader organization, driving strategic initiatives across runtime and accelerator performance. You'll coordinate model launches, manage cross-platform dependencies, and ensure reliability across multiple hardware targets, all while keeping infrastructure teams aligned with Research, Product, and Safety priorities.

Requirements

• Several years of TPM experience delivering complex infrastructure programs
• Deep technical understanding of inference systems, compilers, or hardware accelerators
• Ability to create structure in ambiguous environments
• Strong stakeholder management skills
• Bachelor's degree in relevant field

Responsibilities

• Lead cross-functional initiatives for new infrastructure integration, establishing clear ownership and timelines
• Identify optimization opportunities and prioritize work that unlocks capacity gains
• Drive end-to-end readiness for model launches across multiple hardware platforms
• Own and prioritize the inference deployment roadmap, managing dependencies
• Establish metrics and dashboards to track infrastructure health and deployment success rates