Technical Program Manager: AI Model Performance & Inference

Baseten; Seattle (WA); On-site; USD 165,000 - 330,000; Full time

Benefits offered by this job

Equity compensation

Comprehensive US medical/dental/vision

Flexible PTO

Parental leave

Fertility and family-building stipend

401(k)

Exposure to ML startups

Job summary

Baseten is hiring a Technical Program Manager to build the planning structures, cadences, and governance for our Model Performance team. You will own end-to-end execution across the portfolio, coordinating with performance engineering, infra, and release stakeholders.

This zero-to-one role shapes how ambitious initiatives become well-governed programs. You will engage with engineers building engines like vLLM, TensorRT-LLM, SGLang, or NVIDIA Dynamo, influencing without authority and

Qualifications

• Deep technical program management experience managing programs of this scope.
• Experience program-managing model performance or inference optimization work with production stacks.
• Ability to navigate ambiguity and build new program structures from scratch.
• Proven ability to influence across engineers, managers, and leadership.
• Excellent written and verbal communication, making technical programs legible.
• High agency decision making with ownership and accountability.

Responsibilities

• Own execution across Model Performance's active project portfolio, enabling tech leads to focus on direction.
• Design and stand up planning structures, cadences, and status reporting.
• Coordinate model release and optimization programs end to end, including day-zero launches.
• Drive cross-team alignment as scope expands to APIs and inference production stack.
• Surface risks and dependencies early and keep leadership informed.
• Partner with engineering leads to design team structures and ownership boundaries as the org scales.

Skills

Technical Program Management

Model Performance Experience

Ambiguity Handling

Influence Without Authority

Communication Skills

Ownership & Accountability

Tools

vLLM

TensorRT-LLM

SGLang

NVIDIA Dynamo

Job description

Baseten is hiring a Technical Program Manager to build the planning structures, cadences, and governance for our Model Performance team. You will own end-to-end execution across the portfolio, coordinating with performance engineering, infra, and release stakeholders.

This zero-to-one role shapes how ambitious initiatives become well-governed programs. You will engage with engineers building engines like vLLM, TensorRT-LLM, SGLang, or NVIDIA Dynamo, influencing without authority and