Principal SRE - AI Inference

Highlights

• Deliver world-class ultra-reliable inference for leading frontier model builders.
• Architect unified capacity management and production control plane at scale.
• Enable safe self-service workflows with strong guardrails for critical operations.

What they offer

• Build breakthrough AI platform beyond GPU constraints
• Publish and open-source cutting-edge AI research
• Work on one of the fastest AI supercomputers in the world
• Job stability with startup vitality
• Non-corporate culture respecting individual beliefs

Ideal candidate

Proven principal engineer who loves turning operational complexity into elegant, reliable automation and sharing reliability as a team discipline for frontier AI at scale.

Requirements

• 15+ years in SRE, infrastructure or platform engineering delivering reliability at large scale
• Deep experience with large-scale compute fleets, control planes, schedulers and capacity management
• Experience defining cross-team architecture for production control planes and self-service platforms
• Hands-on experience with observability, incident response and SLO-based reliability management