AI Runtime Solutions Architect

CoreWeave; Bellevue (WA); On-site; USD 207,000 - 275,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

401(k) with employer match

Catered lunch daily in office

Paid Parental Leave

Flexible PTO

Tuition Reimbursement

Job summary

CoreWeave is seeking a Solution Specialist for AI Runtime Services in Bellevue, WA. You will own commercial and technical strategy for new customer wins in AI runtime infrastructure, focusing on high throughput, low latency model serving through our Inference platform and secure, isolated execution via Sandboxes.

You will translate customer needs into product feedback, develop technical playbooks, and drive adoption with the first wave of customers and industries needing scalable AI deployment.

Qualifications

• 10+ years of experience in distributed systems, ML infrastructure, or production AI engineering.
• 5+ years working with AI runtime systems in a customer-facing capacity.
• Deep knowledge of AI workloads at runtime: serving frameworks, batching, GPU memory management.

Responsibilities

• Own the commercial and technical strategy for net new customer wins in AI runtime infrastructure.
• Drive new business opportunities where latency and throughput are bottlenecks.
• Translate requirements into product feedback that shapes the AI Runtime Services roadmap.
• Develop deal structures and technical playbooks to accelerate opportunities.

Skills

Distributed systems

ML infrastructure

AI runtime systems

Kubernetes

GPU memory management

Performance benchmarking

Tools

vLLM

TensorRT-LLM

Triton

Container runtimes

microVMs

Job description

CoreWeave is seeking a Solution Specialist for AI Runtime Services in Bellevue, WA. You will own commercial and technical strategy for new customer wins in AI runtime infrastructure, focusing on high throughput, low latency model serving through our Inference platform and secure, isolated execution via Sandboxes.

You will translate customer needs into product feedback, develop technical playbooks, and drive adoption with the first wave of customers and industries needing scalable AI deployment.