Senior DevOps/Platform Engineer

About the Company

Shelf is building a unique operating system for an automated future. We provide a platform that models a company's policies, workflows, and operational logic into an AI Data Model, enabling AI Agents to reliably deliver precise outcomes at scale for enterprise customers like Glovo, Nespresso, and HelloFresh.

Responsibilities

• Own the AI platform infrastructure end to end, including model access, deployment, runtime paths, observability, and security
• Build and operate the internal AI gateway and platform services used by product teams
• Enable safe use of cloud-hosted and self-hosted models (LLMs, VLMs, audio models)
• Improve deployment, scaling, monitoring, and incident response for AI-heavy production services
• Build infrastructure as code, CI/CD flows, and developer-friendly paved paths
• Strengthen observability through logs, metrics, traces, and dashboards
• Improve security, access control, and auditability around models and production operations
• Reduce toil through automation and internal tooling

Requirements

• Senior-level experience in DevOps, platform engineering, SRE, or infrastructure engineering
• Strong cloud fundamentals in AWS, GCP, or Azure
• Experience with infrastructure as code and modern delivery pipelines
• Strong operational judgment regarding reliability and incident response
• Security-minded approach to access control and secrets management
• Clear written communication skills for runbooks and postmortems
• AI-native working style using AI tools in daily engineering workflows

Preferred Qualifications

• Experience operating model-serving infrastructure or AI platform services
• Experience improving developer experience (DevEx)
• Experience with GCP
• Ability to debug complex problems across application code and infrastructure