Senior AI Infrastructure Engineer

CoreWeave; Bellevue (WA); On-site; USD 152,000 - 204,000; Full time

Benefits offered by this job

Medical, dental, vision insurance (100

401(k) with employer match

Flexible PTO

Tuition Reimbursement

Employee Stock Purchase Program (ESPP)

Mental Wellness Benefits

Parental Leave

Childcare support

Job summary

CoreWeave is hiring a Senior Engineer to lead the design and optimization of a Kubernetes-native inference platform at scale in the US. You’ll collaborate with product, orchestration, and hardware teams to meet strict P99 SLAs and drive performance improvements across services.

We value deep experience with distributed systems, Python/Go coding, Kubernetes at production scale, and a track record of improving tail latency and reliability through metrics-driven work.

Qualifications

• Strong coding in Python or Go with production experience in distributed systems.
• Hands-on Kubernetes at scale, with CI/CD and observability tooling.
• Familiarity with performance optimization for ML/AI workloads.

Responsibilities

• Lead design reviews and drive architecture within the team; decompose multi-service work into milestones.
• Define and own SLIs/SLOs; ensure post-incident actions land and reliability improves release-over-release.
• Implement optimizations such as micro-batch schedulers and KV-cache reuse with measurable impact.
• Mentor IC1/IC2 engineers and elevate coding/testing standards across teams.
• Own cross-team areas like routing, adaptive scheduling, and GPU resource isolation.

Skills

Python

Go

Distributed systems

Kubernetes

CI/CD

Performance tuning

Tools

CUDA kernels

NCCL/SHARP

RDMA/NUMA

Job description

CoreWeave is hiring a Senior Engineer to lead the design and optimization of a Kubernetes-native inference platform at scale in the US. You’ll collaborate with product, orchestration, and hardware teams to meet strict P99 SLAs and drive performance improvements across services.

We value deep experience with distributed systems, Python/Go coding, Kubernetes at production scale, and a track record of improving tail latency and reliability through metrics-driven work.