(Staff / Senior Staff) AI Inference Reliability Engineer, Compute Infra

Highlights

• Own SLOs and incident response for large-scale inference serving in production.
• Turn postmortems into permanent automated fixes instead of recurring pages.
• Make capacity efficiency safe while keeping fleet fast and stable at scale.

What they offer

• startup equity
• health insurance

Ideal candidate

A builder with production-reliability instincts who loves owning large distributed systems in the real world and turning outages into engineered automation. Product-minded about on-call and motivated by keeping complex fleets efficient without sacrificing stability.

Requirements

• Experience operating a provisioning or host-lifecycle pipeline in production
• Hands-on production-reliability experience on large-scale distributed or GPU-serving systems
• Comfortable troubleshooting InfiniBand/RDMA and Kubernetes controller/CRD-based platforms
• Experience with adapter-based serving and running differentiated SLOs across model pools of different priority
• Demonstrated track record of eliminating operational toil through automation and tooling you built yourself
• Hands-on experience with Kubernetes controller/CRD patterns, reconciliation loops, and node-level health/remediation systems
• Comfort with event-driven architectures, backpressure/circuit-breaking design and built-in observability
• Software-engineering mindset: write and ship production code and treat GPU infrastructure as software to be engineered