Baseten
Technical Program Manager, Model Performance
$165K–$330K
San Francisco +5 · Hybrid · Manager · Full-time · Posted Aug 29, 2026
- Location
- San Francisco
Remote
Toronto
New York
Montreal
Seattle - Experience
- Deep technical program management experience; no specific number of years stated.
About the job
Build the Model Performance organization’s program framework and coordinate technical initiatives that turn inference performance research into production capabilities.
What you'll do
- Own execution across the active project portfolio and establish planning, operating cadences, and status reporting.
- Coordinate model release and optimization programs end to end, aligning performance engineering, infrastructure, and release stakeholders.
- Surface risks and dependencies, keep leadership informed, and support cross-team alignment and organizational scaling.
What they ask for
- Deep technical program management experience running programs of similar or greater scope and organizational complexity.
- Experience program-managing model performance or inference optimization work, including familiarity with production serving stacks.
- Experience building programs from the ground up in ambiguous settings.
- Ability to influence across engineering, management, and leadership, with excellent communication and strong ownership.
Nice to have
- Experience coordinating model release programs, including day-zero launches.
- Hands-on software engineering background or deep learning performance optimization experience; inference is preferred.
Pay
$165K – $330K USD base salary
Tools
vLLM, TensorRT-LLM, SGLang, NVIDIA Dynamo
AI focus
Coordinate model performance and inference optimization programs, including model releases and day-zero launches.
Model-written summary · the original posting is authoritative