3 months ago
Amsterdam, Netherlands or London, United KingdomSenior
Responsibilities
- Design and build the Serverless platform control plane, scheduler, runtime, autoscaler, and customer-facing APIs
- Solve cold-start latency, GPU scheduling under contention, multi-tenant isolation, fair-share quotas, and edge request routing
- Set technical direction, own architecture decisions, write design documentation, and align the team
- Raise engineering standards through code reviews, design reviews, and technical leadership
- Define SLOs, build observability, lead incident response, and improve the platform through postmortems
- Work directly with customers on architecture reviews, performance escalations, and production issues
- Partner with Product, GTM, and infrastructure teams to translate customer needs into a technical roadmap
Requirements
- 7+ years of professional software engineering experience shipping production distributed systems at scale
- Excellent knowledge of Golang or readiness to quickly switch to it
- Deep experience with Kubernetes and container orchestration
- Strong understanding of distributed-systems trade-offs and patterns including consistency, availability, queueing, backpressure, retries, idempotency, and multi-tenancy
- Experience designing and operating high-throughput, low-latency services
- Demonstrated ownership of difficult engineering problems and ability to drive design discussions and unblock teammates
- Ability to write reliable code and solve complex problems
- Teamwork-oriented approach
- Coding interview required
- Preferred experience with serverless or function-as-a-service platforms
- Preferred GPU scheduling experience, including Kubernetes device plugins, MIG, MPS, time-slicing, or NVIDIA GPU Operator
- Preferred ML inference experience with model loading and warm-pool strategies
- Preferred cold-start optimization at the runtime, image, or snapshot level
- Preferred experience writing Kubernetes operators with Go, controller-runtime, or kubebuilder
- Open-source contributions in serverless, scheduling, or inference ecosystems are a bonus
Benefits
- Hybrid work from the Amsterdam or London office
- Competitive compensation
- Career growth and learning opportunities
- Flexibility and ownership
- Collaborative and innovative culture
- Opportunity to work on impactful AI projects
- International environment and talented teams
Tech Stack
About Nebius
Nebius builds a full-stack AI cloud offering GPU compute, storage, and tools for training and deploying ML models for startups, enterprises, and research labs. It sells consumption-based cloud infrastructure (IaaS/PaaS) and managed services tailored to generative AI workloads, including large-scale model training and inference. The company is headquartered in Amsterdam and operates as an independent provider.