Director of Engineering, Inference Services

CoreWeave(1 month ago)

HybridFull TimeDirector$206,000 - $303,000Engineering

About this role

The Director of Engineering will lead and scale CoreWeave’s next-generation Inference Platform, owning the technical vision and delivery of low-latency, high-throughput GPU inference services. This strategic role partners with product and infrastructure teams to design, build, and operate global, multi-tenant model-serving runtimes and developer tooling. The director hires and mentors engineering teams, establishes operational standards and SLAs, and shapes cost- and performance-optimized solutions for customers.

View Original Listing

Required Skills

Inference Platform
Model Serving
GPU Optimization
Kubernetes
Autoscaling
Micro-Batching
Low-Latency Networking
Model Optimization
Observability
SLOs

+8 more

Qualifications

Bachelor’s in CS, EE, or Related
Master’s in CS, EE, or Related
U.S. Person or Export Authorization Eligible

About CoreWeave

coreweave.com

CoreWeave is a cloud provider purpose-built for GPU-accelerated AI and high-performance compute workloads, positioning itself as "The Essential Cloud for AI." It offers on-demand and dedicated GPU infrastructure (bare metal, virtual machines, and Kubernetes), high-performance networking and storage, and managed services to support large-scale training, inference, and graphics rendering. CoreWeave emphasizes performance, cost-efficiency, and operational support so enterprises and research teams can deploy and scale AI workloads with predictable performance and security.