Technical Program Manager, Inference Performance
Core
Bridge between inference systems and the broader organization, driving strategic initiatives for inference runtime and accelerator performance.
Role type
Technical Program Manager, Inference Performance
Builds
Inference runtime and accelerator performance infrastructure for large language models
Domain
AI Infrastructure / Large Language Model Deployment
Deliverable
infrastructure
Required skills
Technical program management, Inference systems knowledge, Compiler or hardware accelerator understanding, Cross-functional coordination, Strategic planning, Stakeholder management, Process improvement
Preferred skills
Experience with infrastructure scaling, Hardware integrations, Deployment governance, Ambiguous environment navigation
Technologies
Inference runtime, Hardware accelerators, Large language models
Responsibilities
Lead cross-functional initiatives for new infrastructure integration, Partner with engineering teams to identify optimization opportunities, Drive end-to-end readiness for model and feature launches, Own and prioritize the inference deployment roadmap, Build strong relationships across research, engineering, and product teams, Identify inefficiencies in current workflows and drive systematic improvements
Seniority
Mid-to-Senior, hands-on IC
