Fleet SRE: Inference Systems Reliability & Telemetry

Etched; San Jose (CA); On-site; USD 150,000 - 190,000; Full time

Benefits offered by this job

Medical, dental, and vision packages

Housing subsidy of $2,500 per month

Relocation support for San Jose

Daily lunch and dinner in our office

Unlimited compute budget

Job summary

Etched in San Jose is seeking a Site Reliability Engineer to build the command–and–control layer for frontier inference systems. You’ll define healthy signals, set alerting, and design agentic health workflows, enabling automated recovery and targeted handoffs.

You’ll work with Supercomputing and Infrastructure to shape telemetry, implement OpenTelemetry tracing, and run on‑call rotations across time zones. The role emphasizes reliability, incident management and scalable fleet operations.

Qualifications

• 2+ years in site reliability, production engineering or infrastructure for large‑scale production systems (8+ years for the San Jose lead seat).
• Defined alerting standards used by several teams; knowledge of SLOs, error budgets and alert design.

Responsibilities

• Define what a healthy inference system looks like and decide which actions run automatically vs. require a human.
• Set a common alerting standard with SLOs, latency, error rate and availability metrics.

Skills

Site reliability

Prometheus

Grafana

SLOs and alerts

On-call incidents

Python / Go / Rust

Linux

Kubernetes

Terraform / Ansible

Tools

OpenTelemetry

PCIe troubleshooting

Job description

Etched in San Jose is seeking a Site Reliability Engineer to build the command–and–control layer for frontier inference systems. You’ll define healthy signals, set alerting, and design agentic health workflows, enabling automated recovery and targeted handoffs.

You’ll work with Supercomputing and Infrastructure to shape telemetry, implement OpenTelemetry tracing, and run on‑call rotations across time zones. The role emphasizes reliability, incident management and scalable fleet operations.