Technical Program Manager, Inference Performance

As a Technical Program Manager for Inference, you'll drive strategic initiatives across inference runtime and accelerator performance—coordinating model launches, managing cross-platform dependencies, and ensuring reliability across multiple hardware targets. This role is essential for keeping our most contended infrastructure teams shipping effectively while Research, Product, and Safety all depend on their output.

Requirements

• Several years of experience in technical program management
• Proven success delivering complex infrastructure programs, preferably in ML/AI systems or large-scale distributed systems
• Deep technical understanding of inference systems, compilers, or hardware accelerators
• Strong stakeholder management skills and ability to build trust with technical and non-technical partners
• Experience with infrastructure scaling initiatives, hardware integrations, or deployment governance
• Ability to balance strategic planning with tactical execution

Benefits

• Competitive compensation
• Benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space