SRE: AI Observability for LLM Platform

Appnovation; Austin (TX); On-site; USD 130,000 - 180,000; Full time

Job summary

Appnovation in Austin, TX is seeking a Site Reliability Engineer to design and implement the observability platform for LLM-based applications. You will own incidents, runbooks, and the onboarding path for internal teams relying on a robust platform.

Role requires hands-on Kubernetes on AWS (EKS), ClickHouse/Redis/PostgreSQL ops, and building monitoring and SLAs from scratch. Consulting experience and calm, process-driven problem solving are valued.

Qualifications

• Hands-on experience with Kubernetes on AWS (EKS)
• Experience with ClickHouse, PostgreSQL and Redis in production
• Experience building monitoring, alerting and service levels from scratch
• Strong incident management and runbook/documentation skills
• Consulting experience and ability to work with client teams

Responsibilities

• Diagnose and resolve platform failures across ClickHouse, PostgreSQL, Redis, and the Kubernetes layer
• Build and maintain monitoring, alerting, and SLAs from scratch
• Own backups, restores, and disaster recovery runbooks
• Plan safe upgrades with rollback strategies
• Triage onboarding and support paths for internal teams

Job description

Appnovation in Austin, TX is seeking a Site Reliability Engineer to design and implement the observability platform for LLM-based applications. You will own incidents, runbooks, and the onboarding path for internal teams relying on a robust platform.

Role requires hands-on Kubernetes on AWS (EKS), ClickHouse/Redis/PostgreSQL ops, and building monitoring and SLAs from scratch. Consulting experience and calm, process-driven problem solving are valued.