Senior Site Reliability Engineer, Site Lead

The role

You will build and lead the European engineering team to manage critical infrastructure for a global inference cloud. You will recruit engineers, set technical direction, and contribute to architecture and implementation for GPU fleets and distributed systems.

What you will do

• Build the European engineering team by recruiting, hiring, and developing engineers.
• Translate company priorities into a focused roadmap and make technical tradeoffs.
• Contribute to architecture, review designs and code, and work on technical problems.
• Lead improvements to Kubernetes infrastructure for provisioning, networking, storage, and deployment.
• Build isolation, failover, observability, and recovery to improve reliability.
• Establish sustainable incident response.
• Automate capacity expansion, deployments, and maintenance.
• Establish clear ownership, documentation, and handoffs across time zones.
• Set a high bar for technical quality, accountability, and collaboration.

Required qualifications

• Experience leading engineering teams responsible for production infrastructure or distributed systems.
• Track record of hiring and developing engineers, setting priorities, and delivering technical outcomes.
• Technical depth to guide architecture and contribute directly.
• Experience building and operating reliable services with production ownership.
• Strong Linux fundamentals.
• Practical knowledge of networking, storage, containers, and Kubernetes.
• Ability to write maintainable software and automation.
• Systematic approach to debugging problems across application, cluster, network, and hardware boundaries.
• Clear communication and experience working across teams and time zones.

Nice to have

• Experience establishing or growing an engineering office or regional team.
• Experience with multi-region, multi-provider, or bare-metal infrastructure.
• Familiarity with GPUs, model serving, or inference systems such as vLLM or SGLang.
• Experience building highly available services, multi-tenant platforms, or distributed data systems.
• Experience leading teams through rapid growth while maintaining technical quality and sustainable operations.

About the company

Parasail delivers an enterprise-grade inference cloud for open-weight models. They have raised a $32 million Series A and are scaling beyond trillions of tokens a day.