Site Reliability Engineer (SRE)

Role overview Own the reliability, availability, and performance of production deployment infrastructure supporting AI applications, GPU workloads, and distributed node services. This hands-on SRE role combines software engineering with infrastructure operations, with responsibility for shaping reliability practices and responding to incidents in a remote environment.

Responsibilities - Improve production reliability and performance, with a stated availability target of 99.95% or higher. - Build and maintain observability for metrics, logs, and distributed traces. - Develop deployment pipelines and automate recurring operational work. - Define service-level objectives and indicators with product engineers before features launch. - Scale Kubernetes infrastructure for GPU compute and model inference, and strengthen secrets, network, and runtime security. - Join a 24/7 on-call rotation, lead blameless incident reviews, and use automation to support runbooks and incident triage.

Requirements - 3–6 years in SRE, DevOps, or platform engineering. - Strong Kubernetes and container orchestration experience; CKA or CKAD certification is preferred. - Proficiency in at least one of Go, Rust, or Python. - Experience with AWS, GCP, or bare-metal cloud-native infrastructure. - A track record operating production systems at significant scale and handling incidents under pressure.

Nice to have - Experience managing GPU clusters or AI/ML inference infrastructure. - Familiarity with validator, RPC, or archive node operations; internal developer platforms; or open-source infrastructure projects.

Benefits and work setup Remote role with a fair on-call rotation and an incident bonus. Compensation includes salary and equity, plus health benefits and flexible paid time off. The role offers direct involvement in infrastructure architecture decisions.