Technical Program Manager, Model Performance

About this role

Build the first technical program management function for Baseten’s Model Performance organization. Establish planning, execution, reporting, and coordination practices that help turn inference performance research into production capabilities.

About the company

Baseten is an inference cloud that helps companies run and scale AI models in production with flexible infrastructure and developer tooling.

The team

Model Performance organization, within EPD, Engineering, and Inference.

Stack

What you'll do

• Coordinate execution across the Model Performance project portfolio.
• Create planning structures, operating cadences, and status reporting.
• Manage model release and optimization programs, including day-zero launches.
• Align work across performance engineering, infrastructure, Model APIs, and the inference production stack.
• Identify risks and dependencies and communicate status to leadership.
• Partner with engineering leads on team structure and ownership boundaries.

What we're looking for

• Deep technical program management experience at a similarly complex organization.
• Experience managing model performance or inference optimization programs.
• Working knowledge of production serving engines such as vLLM, TensorRT-LLM, SGLang, or NVIDIA Dynamo.
• Experience building programs from the ground up and working through ambiguity.
• Ability to influence engineers, managers, and leaders without direct authority.
• Strong communication, ownership, and decision-making skills.

Nice to have

• Experience coordinating large-model releases and day-zero launches.
• Hands-on software engineering background.
• Deep learning performance optimization experience, preferably in inference.

Benefits

• Equity
• 100% medical, dental, and vision coverage for employees and dependents in the U.S.
• Flexible PTO and company-wide winter break
• Paid parental leave
• Fertility and family-building stipend
• Company-facilitated 401(k) in the U.S.