Staff Software Engineer, AI Inference Platform

Coreweave; Warszawa; On-site; PLN 260,000 - 480,000; Full time

Benefits offered by this job

Medical Insurance

Dental Insurance

Pension

Life Insurance

Critical Illness Cover

Employee Assistance

Tuition Reimbursement

Job summary

CoreWeave’s Inference team builds and operates the core cloud platform powering massive-scale GPU workloads for AI/ML, VFX, rendering, and real-time inference. As a Staff Software Engineer, you will drive architecture, performance, and reliability across multiple teams, delivering cross-cutting design initiatives and advanced inference optimisations.

You will define scalable systems, lead SLI/SLO ownership, and mentor engineers while pushing for low-latency, cost-efficient, high-uptime cloud

Qualifications

• Bachelor’s degree in Computer Science, Engineering, or related technical field.
• 8+ years of experience building large-scale distributed systems or cloud platforms.
• Strong coding proficiency in Go, Python, or C++.
• Deep expertise in Kubernetes at production scale.
• Strong understanding of networked systems, performance optimisation.
• Hands-on experience with inference systems including batching, caching, memory optimisation, mixed precision, streaming token delivery.
• Proven ability to improve tail latency (P95/P99) and reliability.
• Experience owning system-wide SLIs/SLOs and autoscaling strategies.

Responsibilities

• Define and lead architecture, performance, and reliability for Kubernetes-based inference platform.
• Lead cross-team design initiatives across routing, adaptive scheduling, and resource management.
• Implement advanced inference optimisations such as speculative decoding and KV-cache reuse.
• Establish benchmarking frameworks and observability across infrastructure boundaries.
• Mentor engineers and raise engineering rigour across the org.

Skills

Go

Python

C++

Kubernetes

Distributed systems

Batching

Caching

Memory optimisation

BF16/FP8

Streaming

SLIs/SLOs

Autoscaling

Education

Bachelor’s degree in Computer Science/Engineering

Tools

CUDA

NCCL

RDMA

NUMA

GPU interconnects

vLLM

Triton

TensorRT-LLM

Ray Serve

TorchServe

Job description

CoreWeave’s Inference team builds and operates the core cloud platform powering massive-scale GPU workloads for AI/ML, VFX, rendering, and real-time inference. As a Staff Software Engineer, you will drive architecture, performance, and reliability across multiple teams, delivering cross-cutting design initiatives and advanced inference optimisations.

You will define scalable systems, lead SLI/SLO ownership, and mentor engineers while pushing for low-latency, cost-efficient, high-uptime cloud