Senior SRE: Reliability & Inference Systems Lead

Vizcom; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Vizcom is seeking a Senior SRE to join our small, fast-moving team in San Francisco. You’ll become the second SRE, share responsibility with an on-board teammate, and help transform SRE into a true, high-visibility function that enables product engineering to ship daily without breaking the system.

You will lead incident response, design reliable pipelines, and drive observability initiatives across Kubernetes, AWS, and multi-provider inference workloads.

Qualifications

• 5+ years running production systems.
• Strong on observability, incident response and root cause analysis.
• Comfortable with Kubernetes, networking and AWS.
• Infrastructure-as-code experience (Pulumi, Terraform or similar).
• Can read and fix application code (TypeScript).
• Think in failure modes and blast radius by default.
• Own problems end to end; not just filing tickets.
• Clear written communication; postmortems and RFCs are part of the job.

Responsibilities

• Define SLOs for surfaces (API, websockets, jobs, renders); measure and enforce them.
• Improve inference reliability: provider failover, model fallbacks, queue priorities.
• Manage Kubernetes and infra: Probes, rollouts, autoscaling, Pulumi.”,

Skills

Observability

Incident response

Root cause analysis

End-to-end ownership

Communication

Education

Bachelor's degree in CS or equivalent

Tools

Kubernetes

AWS

Pulumi

Terraform

Job description

Vizcom is seeking a Senior SRE to join our small, fast-moving team in San Francisco. You’ll become the second SRE, share responsibility with an on-board teammate, and help transform SRE into a true, high-visibility function that enables product engineering to ship daily without breaking the system.

You will lead incident response, design reliable pipelines, and drive observability initiatives across Kubernetes, AWS, and multi-provider inference workloads.