Technical Program Manager, Model

• • Own execution across Model Performance's active project portfolio
• • Design and establish planning structures, operating cadences, and status reporting mechanisms
• • Coordinate model release and optimization programs end to end, including day-zero launches
• • Sequence work across performance engineering, infrastructure, 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 organization scales

• Deep technical program management experience; already running programs of this scope at an organization of similar or greater complexity
• Experience program-managing model performance or inference optimization work
• Understanding of how vLLM, TensorRT-LLM, SGLang, or NVIDIA Dynamo fit into a production serving stack
• Comfort with ambiguity and zero-to-one program building
• Ability to influence without authority across engineers, managers, and leadership
• Excellent written and verbal communication
• High-agency decision making demonstrating ownership, accountability, and a strong desire to get things done

Demonstrates deep technical program management expertise with a focus on model performance and inference optimization. Capable of driving cross-team alignment and managing complex projects while maintaining clear communication and accountability.

• Technical Program Management
• Model Performance Optimization
• Cross-Team Alignment
• Influencing Without Authority
• High-Agency Decision Making

• Program Management
• Model Optimization
• Project Execution
• Risk Management
• Status Reporting

• Excellent Communication
• Comfort with Ambiguity
• Ownership
• Accountability

• Model Performance
• Inference Production Stack
• Performance Engineering
• Project Portfolio Management

• VLLM
• TensorRT-LLM
• SGLang
• NVIDIA Dynamo