Site Reliability Engineer

About this role

Own and improve the reliability of Baseten’s multi-cloud Kubernetes infrastructure and ML serving platform. Build observability, operational processes, and automated mitigations to help teams respond safely and effectively to incidents.

About the company

Baseten is an inference cloud that helps companies run and scale AI models in production with flexible infrastructure and developer tooling.

The team

SRE team within EPD, Engineering, and Infrastructure.

Stack

What you'll do

• Own infrastructure reliability, incident response, post-mortems, and remediation tracking.
• Build observability infrastructure for metrics, logs, dashboards, and alerting as code.
• Create and improve runbooks for recurring failures.
• Automate mitigations and self-healing for frequent failure patterns.
• Diagnose runtime issues involving latency, memory, GPU utilization, concurrency, and model lifecycle.
• Define and instrument SLOs and SLIs for customer workloads and internal services.

What we're looking for

• Extensive hands-on Kubernetes experience.
• Experience building and maintaining scalable infrastructure.
• Strong foundation in observability tools and alerting pipelines.
• Experience with infrastructure as code and GitOps workflows.
• Experience writing runbooks, leading incident response, and conducting post-mortems.
• Able to work across engineering and operations, combining coding with sound operational processes.

Nice to have

• Multi-cloud experience, such as EKS or GKE.
• Observability-as-code experience.
• Familiarity with incident management platforms such as incident.io.
• Curiosity about deploying and serving ML models at scale.

Benefits

• Meaningful equity.
• Medical, dental, and vision insurance fully covered for U.S. employees and dependents.
• Flexible PTO and company-wide winter break.
• Paid parental leave.
• Fertility and family-building stipend.
• Company-facilitated 401(k) for U.S. employees.