Strategic TPM for Model Performance & Inference

Precision Labs; San Francisco (CA); Hybrid; USD 150,000 - 210,000; Full time

Benefits offered by this job

Equity

Flexible PTO

Parental leave

401(k)

Learning & networking opportunities

Job summary

Baseten in San Francisco is seeking a Technical Program Manager for the Model Performance organization to build the core planning and governance for high-performance inference initiatives. You will own the end-to-end execution of active projects and drive cross-functional alignment across engineering, infra, and product teams.

This zero-to-one role requires turning loosely defined initiatives into predictable programs, with strong emphasis on transparency, metrics, and scalable processes.

Qualifications

• Deep technical program management experience on programs of similar complexity.
• Experience in model performance or inference optimization with production stacks.
• Ability to build new planning structures and governance from scratch.
• Ability to influence across engineers, managers, and leadership.

Responsibilities

• Own execution across Model Performance's active project portfolio.
• Design and stand up planning structures, cadences, and status reporting.
• Coordinate model release and optimization programs end to end.
• Drive cross-team alignment as scope expands within the org.
• Surface risks and dependencies early and keep leadership informed.
• Partner with engineering leads to define team structures and ownership.

Skills

Technical program management

Cross-functional collaboration

Communication

Strategic planning

Tools

vLLM

TensorRT-LLM

SGLang

NVIDIA Dynamo

Job description

Baseten in San Francisco is seeking a Technical Program Manager for the Model Performance organization to build the core planning and governance for high-performance inference initiatives. You will own the end-to-end execution of active projects and drive cross-functional alignment across engineering, infra, and product teams.

This zero-to-one role requires turning loosely defined initiatives into predictable programs, with strong emphasis on transparency, metrics, and scalable processes.