Technical Program Manager Model Performance

Baseten is an AI inference platform for deploying, optimizing, and scaling custom, open-source, and fine-tuned models in production.

San Francisco, United States
About Baseten

Baseten provides model runtimes, inference infrastructure, developer workflows, and deployment options including managed cloud, self-hosted, and hybrid environments.

View jobs by Baseten

Skills

About the Role

You will build the planning structure, execution processes, metrics, and reporting mechanisms for model-performance work. You will coordinate model releases and optimization programs, align stakeholders across engineering groups, surface risks and dependencies, and help define ownership as the organization scales.

Requirements

  • Technical program management
  • Model performance
  • Inference optimization
  • vLLM
  • TensorRT-LLM
  • SGLang
  • NVIDIA Dynamo
  • Program building
  • Cross-functional influence
  • Written communication
  • Verbal communication

Responsibilities

  • Own execution across the active Model Performance project portfolio
  • Design planning structures, operating cadences, and status reporting
  • Coordinate model-release and optimization programs end to end
  • Drive cross-team alignment across performance engineering, infrastructure, and release stakeholders
  • Surface risks and dependencies and inform leadership of status
  • Partner with engineering leads on team structures and ownership boundaries

Benefits

  • Equity
  • 100% medical, dental, and vision insurance coverage for U.S. employees and dependents
  • Flexible PTO
  • Company-wide winter break
  • Paid parental leave
  • Fertility and family-building stipend through Carrot
  • Company-facilitated 401(k) for U.S. employees
Technical Program Manager Model Performance at Baseten | JobStash