Technical Program Manager – Inference

CoreWeave’s AI/ML Platform Services organization builds the distributed systems that power large-scale inference workloads across our GPU-accelerated cloud. As a Technical Program Manager focused on distributed inference, model onboarding, and runtime optimization, you will drive programs that enable AI models to serve billions of inferences reliably and efficiently.

You’ll partner closely with engineering, product, and marketing teams to deliver scalable, performant model-serving systems—reducing latency, improving GPU utilization, and making it easier for customers and internal teams to onboard and optimize AI models on CoreWeave.

This role is ideal for someone who thrives in complex, cross-functional environments, has deep technical fluency in distributed systems or ML infrastructure or Gen AI, and excels at creating structure, visibility, and execution rhythm across multiple teams.

• Drive end-to-end program management for distributed inference platform initiatives, including scaling, reliability, and performance optimization.
  
• Lead cross-functional programs for model onboarding — defining standardized workflows for integrating, validating, and deploying customer and foundation models on CoreWeave.
  
• Partner with engineering and product to define and deliver roadmap outcomes for serving throughput, latency, and cost efficiency.
  
• Coordinate multi-team execution across AI runtime, GPU infrastructure, and DevOps to deliver high-availability inference services.
  
• Build and operationalize success metrics, dashboards, and launch gates to measure reliability, efficiency, and quality across the inference stack.
  
• Collaborate with Product, Engineering, and Marketing on GTM readiness — ensuring technical enablement, documentation, and launch processes align with customer adoption and commercial rollout timelines.
  
• Establish repeatable processes for rollout management, performance regression tracking, and postmortem analysis.
  
• Create and lead operating cadences (program reviews, launch readiness, and retrospectives) to improve visibility and execution velocity.
  
• Collaborate with other TPMs and technical leads across CoreWeave to ensure platform-wide alignment on reliability, scalability, and release practices.
  

• Bachelor’s degree in a technical field or equivalent experience.
  
• 8+ years of program management experience in distributed systems, cloud infrastructure, or AI/ML platform engineering.
  
• Proven experience driving large-scale serving or infrastructure programs from concept to production.
  
• Strong technical fluency in GPU compute, distributed inference systems, container orchestration, and cloud-native architectures.
  
• Demonstrated success in driving measurable improvements in performance, reliability, or operational efficiency.
  
• Excellent written and verbal communication skills, with the ability to align engineering, product, and leadership stakeholders around shared goals.

• Familiarity with inference-serving frameworks (e.g., vLLM, SGLang).
  
• Experience with model onboarding workflows, rollout strategies, and observability tooling (Prometheus, Grafana).
  
• Understanding of ML workloads, GPU resource management, and performance optimization techniques.
  
• Experience defining or maturing technical program structures across multiple teams in a high-growth or startup environment.

The base salary range for this role is $180,000 to $264,000. The starting salary will be determined based on job-related knowledge, skills, experience, and market location. We strive for both market alignment and internal equity when determining compensation. In addition to base salary, our total rewards package includes a discretionary bonus, equity awards, and a comprehensive benefits program (all based on eligibility).