Remote SRE: AI-Driven Reliability & Observability

Baseten; United States; On-site; USD 140,000 - 180,000; Full time

Benefits offered by this job

Remote‑first

In-person team summits

Unlimited PTO

Healthcare coverage

Parental leave

Job summary

Baseten is seeking an experienced Site Reliability Engineer to define day-2 operations for our ML infrastructure. You will build robust systems, automations, and observability tools to keep Baseten reliable at scale, collaborating with engineering, product, and forward‑deployed teams to turn failure patterns into automated mitigations.

You will own multi-cloud Kubernetes reliability, develop runbooks, and instrument SLOs/SLIs with a focus on low-context, safe execution.

Qualifications

• Strong foundation in observability tooling (metrics, logging, dashboards)
• Kubernetes multi-cloud experience (EKS, GKE, or similar)
• Experience with Terraform/Helm and GitOps workflows (Flux CD, ArgoCD)
• Incident management experience and post-mortem analysis
• Experience writing runbooks and leading incident response
• Familiarity with infrastructure-as-code and scalable infra design
• Interest in ML model deployment and serving at scale

Responsibilities

• Define and codify the gold standards of day 2 operations for our ML infrastructure platform
• Build robust systems, processes, automations, and observability tooling for reliability at scale
• Collaborate with engineering, forward‑deployed and product teams to convert failures into automated mitigations
• Improve SRE practices by instrumenting SLOs and SLIs, and improving alerting and observability
• Develop AI-assisted tooling for incident triage and response
• Own the reliability of multi-cloud Kubernetes infrastructure, including post‑mortems and remediation tracking
• Create and maintain observability infrastructure—metrics, logging, dashboards, and alerting—as code
• Author and improve runbooks for recurring failures for low-context, safe execution
• Identify high-frequency failure patterns and convert them into automated mitigations or self‑healing automations
• Diagnose runtime issues related to latency, memory, GPU utilization, concurrency, and model lifecycle management
• Define SLOs/SLIs across customer workloads and internal services
• Navigate ambiguity and balance tradeoffs to avoid unnecessary complexity

Skills

Observability tooling

Runbooks & incident response

Kubernetes multi-cloud

Terraform & Helm

GitOps (Flux/ArgoCD)

Incident management

Tools

VictoriaMetrics

Prometheus

Loki

ELK

Grafana

Flux CD

ArgoCD

Terraform

Helm

incident.io

Job description

Baseten is seeking an experienced Site Reliability Engineer to define day-2 operations for our ML infrastructure. You will build robust systems, automations, and observability tools to keep Baseten reliable at scale, collaborating with engineering, product, and forward‑deployed teams to turn failure patterns into automated mitigations.

You will own multi-cloud Kubernetes reliability, develop runbooks, and instrument SLOs/SLIs with a focus on low-context, safe execution.