Tech Lead: AI Backend on Kubernetes & GPU (NL-based)

Nebul; Leiden; On-site; EUR 120,000 - 180,000; Full time

Job summary

Nebul in Leiden is building Europe’s sovereign AI cloud and seeks a Tech Lead – AI Backend, Kubernetes & GPU Platform to shape the architecture behind our AI platform. You’ll design scalable backend systems, APIs and orchestration that run AI workloads across Kubernetes and GPU infrastructure, including LLM inference and model serving.

You’ll guide engineers, lead design discussions, and set standards for reliability, observability, testing and maintainability.

Qualifications

• Extensive Go backend experience in production systems.
• Strong background in designing large-scale microservices.
• Proven track record in technical leadership roles.
• Experience with cloud-native environments and Kubernetes.

Responsibilities

• Design scalable backend systems for AI workloads on Kubernetes with GPU infrastructure.
• Lead architectural decisions for microservices, APIs, and orchestration services.
• Guide engineering teams, review designs, and set reliability standards.
• Collaborate with AI, platform, infra and networking teams to ensure integrated systems.

Skills

Go / Golang

Backend engineering

Distributed systems

Technical leadership

Tools

Kubernetes

GPU orchestration

Cloud-native

NVIDIA infrastructure

vLLM

Triton

KServe

Kafka

Redis

NATS

OpenTelemetry

Job description

Nebul in Leiden is building Europe’s sovereign AI cloud and seeks a Tech Lead – AI Backend, Kubernetes & GPU Platform to shape the architecture behind our AI platform. You’ll design scalable backend systems, APIs and orchestration that run AI workloads across Kubernetes and GPU infrastructure, including LLM inference and model serving.

You’ll guide engineers, lead design discussions, and set standards for reliability, observability, testing and maintainability.