Senior Distributed Systems Engineer (Rust/Kubernetes)

Location: San Francisco, United States; in person five days a week

Company

hirify.global is building a globally distributed inference cloud that runs customer requests on its own GPU fleet across multiple clouds. The platform processes more than 800B tokens per day and operates on Kubernetes.

What you will do

• Build and operate the routing layer that determines which machine handles each inference request.
• Design behavior for demand exceeding available capacity, including scheduling and load management.
• Manage fleet growth and reduction across multiple cloud providers as demand changes.
• Develop and operate Rust services and Kubernetes services for the multi-cloud fleet.
• Own production systems where latency, reliability, and failure behavior directly affect performance.

Requirements

• Around five or more years building real production systems where latency and failure behavior mattered, such as serving systems, control planes, schedulers, databases, networking, or trading systems; data pipelines and analytics do not qualify.
• Strong knowledge of at least one systems programming language: Rust, C++, or Go.
• Experience owning a production system that ran under load and explaining a production failure personally debugged in detail.
• Advanced Kubernetes experience, including extending Kubernetes, particularly on low-reliability infrastructure.

Nice to have

• Real project experience with a scheduler or load balancer.
• Experience working with spot or preemptible capacity.
• Exposure to AI serving systems.

Culture & Benefits

• On-site work in San Francisco five days per week.
• Senior-level scope with significant responsibility and room to grow in a small team.
• Competitive compensation plus equity.