Senior Serverless AI Platform Engineer

Nebius; Greater London; Hybrid; GBP 110,000 - 160,000; Full time

Benefits offered by this job

Competitive compensation

Career growth

Flexibility and ownership

Collaborative culture

Impactful AI projects

International teams

Job summary

Nebius, a leading cloud AI infra, seeks a Senior Software Engineer to build Nebius Serverless AI. You will own the architecture, drive design decisions, and raise the bar through code and design reviews. The role is hybrid from London or Amsterdam, with end-to-end responsibility from runtime to API contracts.

You will design core components, tackle cold-start latency, GPU scheduling, multi-tenant isolation, and collaborate with Product and Infra teams to deliver a coherent technical roadmap.

Qualifications

• 7+ years of professional software engineering experience.
• Excellent knowledge of Golang, or be ready to switch quickly to it.
• Deep experience with Kubernetes and container orchestration.
• Strong distributed-systems instincts: consistency vs. availability, backpressure, multi-tenancy.
• Experience designing high-throughput, low-latency services.
• Ability to drive design discussions and unblock teammates.

Responsibilities

• Design and build core components of the Serverless platform: control plane, scheduler, runtime, autoscaler, and APIs.
• Own hard engineering problems: cold-start latency; GPU scheduling under contention; multi-tenant isolation.
• Set technical direction, write design docs, and align the team behind approaches.
• Raise engineering bar through reviews and mentoring, acting as a senior presence.
• Run the service like an SRE: define SLOs, observability, incident response, postmortems.
• Collaborate with Product, GTM, and infra teams to translate customer needs into a roadmap.

Skills

Golang

Kubernetes

Distributed systems

Performance optimization

Tools

Kubernetes

Knative

Kubebuilder

Job description

Nebius, a leading cloud AI infra, seeks a Senior Software Engineer to build Nebius Serverless AI. You will own the architecture, drive design decisions, and raise the bar through code and design reviews. The role is hybrid from London or Amsterdam, with end-to-end responsibility from runtime to API contracts.

You will design core components, tackle cold-start latency, GPU scheduling, multi-tenant isolation, and collaborate with Product and Infra teams to deliver a coherent technical roadmap.