Senior Software Engineer (Serverless)
HybridAmsterdam, North Holland, The Netherlands
Job Summary
Design and build core components of the Serverless platform, including the control plane, scheduler, runtime, autoscaler, and customer-facing APIs. Own the hardest engineering problems such as cold-start latency, GPU scheduling under contention, and multi-tenant isolation. Set technical direction by driving architecture decisions, writing design docs, and conducting code and design reviews to raise the engineering bar. Run the service like an SRE by defining SLOs, building observability, and leading incident response. Work directly with customers on architecture reviews and performance escalations, while partnering with Product and infrastructure teams to translate needs into a technical roadmap. This senior, high-ownership role is hybrid-based in Amsterdam or London. Nebius is building a full-stack AI cloud platform supporting data, model training, and production deployment without complex in-house infrastructure.
Required Qualifications
- 7+ years of professional software engineering experience
- track record of shipping production distributed systems at scale
- Excellent knowledge of Golang
- Deep experience with Kubernetes and container orchestration
- Strong distributed-systems instincts
- Experience designing and operating high-throughput, low-latency services
- history of being the engineer others look to on hard problems
- Ability to write reliable code and dig into complex problems
- Teamwork-oriented approach
- Work from our office in Amsterdam or London, hybrid
Desired Qualifications
- Experience building serverless or function-as-a-service platforms (Knative, AWS Lambda, GCP Cloud Run, Cloudflare Workers, Modal, Replicate, Together, Fireworks, Anyscale, or similar)
- GPU scheduling experience — Kubernetes device plugins, MIG, MPS, time-slicing, NVIDIA GPU Operator
- ML inference experience — vLLM, TensorRT-LLM, Triton Inference Server, SGLang, model loading and warm-pool strategies
- Cold-start optimization at the runtime, image, or snapshot level (FireCracker, gVisor, checkpoint/restore, image streaming)
- Experience writing Kubernetes operators (Go + controller-runtime / kubebuilder)
- Contributions to relevant open-source projects in the serverless, scheduling, or inference ecosystems
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.