Technical Program Manager — AI Inference Platform Lead

Neura Market; San Francisco, Northern (CA, KY); Hybrid; USD 140,000 - 210,000; Full time

Benefits offered by this job

Equity

Medical coverage

Flexible PTO

Parental leave

401(k)

Learning opportunities

Job summary

Baseten is seeking a Technical Program Manager to join our Model Performance group. This zero-to-one role will build the planning framework, cadence, and cross-functional alignment to accelerate Baseten’s high-performance inference stack.

You will own execution across active projects, coordinate day-zero launches, and work with performance engineering, infra, and release stakeholders. Strong communication is essential for success in this role.

Qualifications

• Experience running programs of high complexity at similar scale.
• Experience with model performance or inference optimization tools.
• Ability to manage ambiguity and build new programs from scratch.
• Proven ability to influence across teams and leadership.
• Excellent written and verbal communication.
• High ownership and accountability.

Responsibilities

• Own execution across active project portfolio in Model Performance.
• Design planning structures, cadences, and status reporting.
• Coordinate model release and optimization programs end to end.
• Drive cross-team alignment as scope expands to APIs and BIS.
• Surface risks and dependencies early; report status to leadership.
• Partner with engineering leads to design team structures.

Skills

Technical program management

Model performance

Inference optimization

Ambiguity handling

Cross-functional influence

Technical communication

Tools

vLLM

TensorRT-LLM

SGLang

NVIDIA Dynamo

Job description

Baseten is seeking a Technical Program Manager to join our Model Performance group. This zero-to-one role will build the planning framework, cadence, and cross-functional alignment to accelerate Baseten’s high-performance inference stack.

You will own execution across active projects, coordinate day-zero launches, and work with performance engineering, infra, and release stakeholders. Strong communication is essential for success in this role.