Technical Program Manager, Inference

What You ll Do:

The AI/ML TPM team owns delivery and execution across Core Weave s AI/ML Platform Services organization. The team partners closely with Product, Engineering, Research, Infrastructure, and Go-to-Market teams to deliver scalable, reliable, and high-performance platforms that support the full AI lifecycle. AI/ML TPMs drive alignment and execution across highly technical, cross-functional teams to ensure the successful delivery of customer-facing infrastructure and platform capabilities used by researchers, engineers, and enterprise customers.

As a Technical Program Manager focused on inference, you will lead complex, cross-functional programs spanning inference platform delivery, customer onboarding, launch readiness, and runtime optimization. The Inference team is responsible for building and operating highly scalable, reliable production inference services for both serverless and dedicated inference use cases. The work spans platform reliability, operational excellence, customer onboarding, release validation, runtime performance, and the launch of new inference capabilities that help customers run models at scale with strong price-performance and low operational friction.

In this role, you will partner with engineering, product, infrastructure, and go-to-market teams to drive programs that improve how inference services are launched, onboarded, operated, and optimized. This includes managing the execution of customer-facing onboarding programs, launch readiness for dedicated inference capabilities, and the platform improvements needed to support scale, reliability, and predictable delivery.

• Drive end-to-end program management for inference platform initiatives spanning reliability, customer onboarding, launch readiness, and runtime optimization
• Lead cross-functional programs for customer onboarding across dedicated and serverless inference offerings, ensuring clear ownership, launch criteria, and readiness for strategic customer use cases
• Drive launch readiness for new inference capabilities by aligning teams around real customer outcomes, supportability, and end-to-end validation
• Partner with engineering and product to define and deliver roadmap outcomes for latency, throughput, uptime, operational quality, and price-performance
• Coordinate multi-team execution across platform, infrastructure, and customer-facing teams to deliver reliable and scalable inference services
• Build and operationalize success metrics, dashboards, launch gates, and review cadences to measure service reliability, onboarding readiness, efficiency, and quality across the inference stack
• Establish repeatable processes for release validation, performance regression tracking, launch management, and postmortem follow-through
• Help unify operational processes, support mechanisms, and execution visibility across inference deployment models and customer onboarding paths
• Create strong communication channels between Engineering, Product, Infrastructure, and Go-to-Market teams to align priorities and deliver predictable, high-impact outcomes

• Bachelor s degree in a technical field or equivalent practical experience
• 8+ years of technical program management experience in distributed systems, cloud infrastructure, or AI/ML platform engineering
• Proven experience driving large-scale infrastructure or platform programs from concept to production in complex, cross-functional environments
• Strong technical fluency in distributed inference systems, GPU compute, cloud-native architectures, and performance optimization
• Demonstrated success driving measurable improvements in reliability, performance, operational readiness, or customer delivery
• Excellent written and verbal communication skills, with the ability to align engineering, product, infrastructure, and customer-facing stakeholders around shared goals
• Experience with inference-serving systems, model onboarding workflows, rollout strategies, and observability tooling
• Familiarity with launch readiness, supportability, incident follow-through, and release validation for production infrastructure or platform services
• Understanding of customer onboarding for…