Senior Site Reliability Engineer

AI companies need inference that’s fast, reliable, and economical at scale. The company delivers it. We’re building an enterprise-grade inference cloud for open-weight models where customers pay for the tokens they use, and we handle everything required to serve them.

Behind one OpenAI-compatible API, we pool GPU capacity from providers around the world and continuously optimize where and how workloads run. That means turning a changing mix of hardware, networks, and infrastructure into a service customers can trust.

We’ve raised a $32 million Series A, and we’re scaling beyond trillions of tokens a day. You’ll have the ownership and reach to shape how we get there.

THE ROLE

At the company, reliability is an engineering problem that spans the entire stack. A GPU fails. A provider goes down. Traffic spikes. Customers still expect their inference to work.

We’re hiring Site Reliability Engineers to build the systems that make that possible. You’ll own infrastructure across our global GPU fleet, write software that automates operations, and make the platform better at detecting, surviving, and recovering from failures.

You’ll work directly with infrastructure, platform, and inference engineers in a flat organization. We welcome SREs, software engineers, platform engineers, and systems engineers who want to build ambitious systems and take responsibility for how they perform in production.

WHAT YOU’LL DO

• Scale a global GPU fleet. Build and improve the Kubernetes infrastructure behind provisioning, networking, storage, and service deployment across providers and regions.

• Make failure survivable. Design better isolation, failover, and recovery so hardware and infrastructure failures have less impact on customers.

• Build software that runs infrastructure. Automate capacity expansion, deployments, and maintenance, eliminating manual work and making changes safer.

• Make the system understandable. Develop observability and diagnostics that reveal bottlenecks, surface failures, and help engineers act quickly.

• Own the production feedback loop. Respond to incidents, get to the root cause, and turn what you learn into stronger systems.

• Push the platform forward. Work across the stack to improve performance, utilization, security, and reliability as inference demand grows.

WHAT YOU BRING

• 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.

Your strongest skill might be software development, distributed systems, or infrastructure operations. We’re building a team with complementary strengths; your previous job title matters less than what you can build and own.

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.

WHY JOIN the company

The systems you build will determine how reliably and efficiently customers can run AI in production. You’ll work close to the hardware, deep in distributed systems, and alongside engineers optimizing the inference stack.

This is a small team tackling problems at substantial scale. You’ll own meaningful architecture decisions, ship improvements directly into production, and help build the foundation for the next stage of AI infrastructure.