Staff Software Engineer, AI Inference Platform

Coreweave; Warszawa; On-site; PLN 321,000 - 428,000; 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

Job summary

CoreWeave, the Essential Cloud for AI, is seeking a Staff Software Engineer (IC5) on the Inference team in Poland. You will act as a technical leader across multiple teams, driving architecture, performance, and reliability for a GPU-accelerated inference platform.

You will own cross-cutting design initiatives, optimize KV-cache and batching strategies, and define SLOs/SLIs while mentoring engineers and raising engineering standards. Light travel may be required.

Qualifications

• Bachelor’s degree in Computer Science, Engineering, or a related technical field.
• 8–12+ years of experience building large-scale distributed systems or cloud platforms.
• Strong coding skills in Go, Python, or C++.
• Deep expertise in Kubernetes at production scale.

Responsibilities

• Lead architecture, performance, and reliability for CoreWeave’s Kubernetes-native inference platform across multiple teams.
• Define and drive complex, cross-cutting design initiatives (request routing, adaptive scheduling, GPU resource management).
• Implement advanced inference optimizations and establish performance benchmarking frameworks.

Skills

Go/Python/C++

Kubernetes

Distributed systems

Performance optimization

Networking

Inference systems

Mentoring engineers

Education

Bachelor’s degree in CS/Engineering

Tools

Kubernetes

Go

Python

C++

Job description

CoreWeave, the Essential Cloud for AI, is seeking a Staff Software Engineer (IC5) on the Inference team in Poland. You will act as a technical leader across multiple teams, driving architecture, performance, and reliability for a GPU-accelerated inference platform.

You will own cross-cutting design initiatives, optimize KV-cache and batching strategies, and define SLOs/SLIs while mentoring engineers and raising engineering standards. Light travel may be required.