Senior Software Engineer (Serverless AI)

TL;DR

Senior Software Engineer (Serverless AI): Building a GPU-native platform for deploying inference endpoints and AI workloads with an accent on control plane architecture, scheduling, and runtime optimization. Focus on solving cold-start latency, GPU scheduling under contention, and ensuring multi-tenant isolation at scale.

Location: Hybrid in Amsterdam, Netherlands or London, United Kingdom. Applicants must be authorized to work in the country in which they apply.

Company

Nebius is building a full-stack AI cloud platform providing GPU orchestration and inference optimization for the global AI economy.

What you will do

• Design and build core components of the Serverless platform, including the control plane, scheduler, runtime, and autoscaler.
• Solve complex engineering problems such as cold-start latency, GPU scheduling under contention, and multi-tenant isolation.
• Set technical direction and drive architectural decisions through design documents and code reviews.
• Manage service reliability by defining SLOs, building observability, and leading incident response.
• Collaborate with customers and internal Product/GTM teams to refine the technical roadmap.

Requirements

• 7+ years of professional software engineering experience with production distributed systems at scale.
• Proficiency in Golang or the ability to quickly transition to it.
• Deep expertise in Kubernetes and container orchestration.
• Strong understanding of distributed systems instincts (consistency vs availability, backpressure, idempotency).
• Experience designing high-throughput, low-latency services.
• Must be authorized to work in the Netherlands or the UK.

Nice to have

• Experience with FaaS platforms (e.g., AWS Lambda, Knative, Modal).
• Knowledge of GPU scheduling (MIG, MPS, NVIDIA GPU Operator).
• Experience with ML inference servers (vLLM, TensorRT-LLM, Triton).
• Cold-start optimization experience (FireCracker, gVisor).
• Proficiency in writing Kubernetes operators.

Culture & Benefits

• Competitive compensation and career growth opportunities.
• High level of flexibility, ownership, and trust.
• Collaborative and innovative international environment.
• Opportunity to work on impactful, cutting-edge AI infrastructure.

Hiring process

• The process includes coding interviews.