Site Reliability Engineer Inference Infrastructure

Skills

About the Role

You will build self-service systems for deploying and operating services, including Kubernetes operators for language-model deployments. You will automate observability and resilience, enable troubleshooting, help meet SLOs through on-call participation, incorporate developer feedback into infrastructure priorities, and share knowledge through reviews.

Requirements

• 5+ years of engineering experience operating large-scale production infrastructure
• Highly available distributed systems, Kubernetes, and GPU workloads
• Kubernetes development, production coding, and support
• GCP, Azure, AWS, OCI, and multi-cloud or hybrid serving
• Linux computing environments
• Compute, storage, network resource, and cost management
• Troubleshooting
• GPU, TPU, or custom accelerator knowledge
• Distributed systems
• Golang or C++

Responsibilities

• Build self-service systems to manage, deploy, and operate services
• Build Kubernetes operators for language-model deployments
• Automate environment observability and resilience
• Enable developers to troubleshoot and resolve problems
• Meet defined SLOs and participate in an on-call rotation
• Incorporate developer feedback into the infrastructure roadmap
• Share knowledge and participate in technical reviews

Benefits

• Weekly lunch stipend of $75/£75 or local equivalent
• Health and dental benefits, including a mental-health budget
• RRSP matching, 401K, and pension scheme
• Parental leave top-up for up to 6 months
• Arts, culture, fitness, wellness, quality-time, and workspace-improvement benefits
• Education and learning stipend
• 6 weeks of paid vacation
• Travel budget for other offices and an annual company offsite
• Co-working benefit
• $500 home-office stipend