Technical Program Manager, Baseten

• Deep technical program management experience - you're already running programs of this scope at an organization of similar or greater complexity
• Experience program-managing model performance or inference optimization work - you understand how engines like vLLM, TensorRT-LLM, SGLang, or NVIDIA Dynamo fit into a production serving stack and can engage credibly with the engineers building on them
• Demonstrated comfort with ambiguity and zero-to-one program building, not just executing an existing framework
• Proven ability to influence without authority across engineers, managers, and leadership who don't report to you
• Excellent written and verbal communication, with the ability to make deeply technical programs legible to any audience
• High agency decision making that demonstrates ownership, accountability and a strong desire to get things done

Desirable

• The Model Performance organization at Baseten is looking to hire our first Technical Program Manager
• This is a zero-to-one role in a team that is responsible for building the core algorithms and methods that power Baseten’s high performance inference stack
• You won't inherit an existing program framework, you'll build one from the ground up: the planning structure, execution processes, metrics and the cross-functional alignment that a fast-growing organization needs
• Your contributions will directly impact how fast our performance R&D gets productized
• If you can drive turning a set of ambitious but loosely defined initiatives into a predictable, well-governed program, this role is for you
• Own execution across Model Performance's active project portfolio, freeing the team's technical leads to focus on technical direction rather than tracking
• Design and stand up the planning structures, operating cadences, and status reporting mechanisms that best fits the team’s DNA
• Coordinate model release and optimization programs end to end, including day-zero launches, sequencing the work across performance engineering, infra, and release stakeholders
• Drive cross-team alignment as scope expands from Model Performance Core into Model APIs and the inference production stack (BIS)
• Surface risks and dependencies early, and keep leadership informed with clear, honest status
• Partner with engineering leads to design team structures and ownership boundaries as the org scales