Senior Site Reliability Engineer

Parasail is building an enterprise-grade inference cloud for open-weight models, pooling GPU capacity from providers around the world behind one OpenAI-compatible API. The Site Reliability Engineer will own infrastructure across the global GPU fleet, write software that automates operations, and improve the platform's ability to detect, survive, and recover from failures. The role works directly with infrastructure, platform, and inference engineers in a flat organization.

Responsibilities

Scale a global GPU fleet by building and improving the Kubernetes infrastructure behind provisioning, networking, storage, and service deployment across providers and regions; Make failure survivable by designing better isolation, failover, and recovery so hardware and infrastructure failures have less impact on customers; Build software that runs infrastructure by automating capacity expansion, deployments, and maintenance; Make the system understandable by developing observability and diagnostics that reveal bottlenecks, surface failures, and help engineers act quickly; Own the production feedback loop by responding to incidents, getting to the root cause, and turning learnings into stronger systems; Push the platform forward by improving performance, utilization, security, and reliability as inference demand grows

Requirements

Experience building and operating production infrastructure or distributed systems, with real ownership of reliability; Strong Linux fundamentals and practical knowledge of networking, storage, and containers; Hands-on experience running Kubernetes in production; The ability to write maintainable software and automation to solve infrastructure problems; A systematic approach to debugging problems that cross application, cluster, network, and hardware boundaries; Good judgment about when to move quickly, when to simplify, and where reliability matters most; The initiative to take a problem from investigation through implementation and work closely with teammates along the way

Nice to have

Experience with multi-region, multi-provider, or bare-metal infrastructure; Familiarity with GPUs, model serving, or inference systems such as vLLM or SGLang; Experience with infrastructure as code, CI/CD, observability, or automated recovery; Experience building highly available services, multi-tenant platforms, or distributed data systems