Member of Technical Staff, Production Site Reliability Engineer

Inferact is hiring a Site Reliability Engineer to ensure the reliability of its vLLM-powered AI inference services in production. The role involves defining SLOs, building monitoring and automation, leading incident response and post-mortems, and partnering with engineering on capacity planning and operational readiness. The ideal candidate thinks about failure before launch and simplifies operations.

Minimum qualifications: Bachelor's degree or equivalent in CS/engineering; experience with production distributed systems; programming in Python, Go, Bash; incident response and root cause analysis; understanding of SLOs/SLIs/error budgets; strong Linux, networking, and debugging skills; clear communication under pressure. Preferred: AI inference/ML infrastructure; Kubernetes; observability; deployment safety; resource scheduling.