Staff Software Engineer, AI Inference Platform

CoreWeave; Greater London; On-site; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Family-level Medical Insurance

Family-level Dental Insurance

Generous Pension Contribution

Life Assurance at 4x Salary

Critical Illness Cover

Employee Assistance Programme

Tuition Reimbursement

Work culture focused on innovative dis

ruption

Job summary

CoreWeave is seeking a Staff Software Engineer for the Inference team to drive architecture and reliability across a Kubernetes-native platform powering large-scale GPU workloads. You will lead cross-team initiatives, optimize performance, and implement advanced inference techniques with robust benchmarking.

The role demands 8+ years in distributed systems, strong Go/Python/C++ skills, and deep Kubernetes expertise, with a focus on tail latency and multi-tenant reliability.

Qualifications

• Bachelor’s degree in Computer Science, Engineering, or related field, or equivalent practical experience.
• 8+ years building large-scale distributed systems or cloud platforms with cross-team leadership.
• Strong coding in Go, Python, or C++ and production Kubernetes expertise.
• Deep knowledge of networked systems, performance tuning, and distributed design.
• Inference systems experience including batching, caching, memory optimization, and mixed precision.
• Proven ability to improve tail latency (P95/P99) and reliability with metrics-driven engineering.

Responsibilities

• Lead architecture, performance, and reliability for the Kubernetes-native inference platform.
• Drive cross-team design initiatives spanning routing, scheduling, and resource management.
• Implement advanced inference optimisations and benchmarking frameworks.
• Establish and own system-wide SLIs/SLOs and capacity planning; mentor senior engineers.

Skills

Go

Python

C++

Kubernetes production

Distributed systems

Performance optimization

Inference systems

Mentoring engineers

SLIs/SLOs

Education

Bachelor's degree in Computer Science or Engineering

Tools

Kubernetes

CUDA

NCCL

RDMA / NUMA

GPU interconnects

Job description

CoreWeave is seeking a Staff Software Engineer for the Inference team to drive architecture and reliability across a Kubernetes-native platform powering large-scale GPU workloads. You will lead cross-team initiatives, optimize performance, and implement advanced inference techniques with robust benchmarking.

The role demands 8+ years in distributed systems, strong Go/Python/C++ skills, and deep Kubernetes expertise, with a focus on tail latency and multi-tenant reliability.