Site Reliability Engineer, Provider Operations at OpenRouter

Confirmed open

OpenRouter seeks a US-remote SRE to monitor AI model providers, automate failover and respond to incidents across its inference routing network.

OpenRouter

Location: Remote
Employment: FullTime
Work arrangement: remote
Technologies: Python, TypeScript, GCP

Create a free application profile — Keep your skills and projects in a reusable profile. Private by default; you choose when to share. Apply for this job directly with the employer.

Role overview

The Provider Operations team needs an engineer to maintain availability and quality of model-provider endpoints. The employer specifies remote work within the United States.

Responsibilities

Build monitoring for latency, throughput, errors, uptime and output quality; define provider SLOs and actionable alerts.
Improve degradation detection and automatic traffic failover, lead provider incident response and postmortems, and create canaries and evaluations for silent quality regressions.
Automate endpoint and capacity operations and load-test providers before large launches.

Qualifications

At least four years in SRE, production engineering or infrastructure for high-traffic services, with strong observability and incident-response practice.
Software engineering ability in TypeScript or Python and knowledge of distributed-system failures are expected. Experience with LLM inference, Cloudflare Workers, Postgres, ClickHouse or traffic routing is useful.

Technology in this role

Python: Software engineering ability in TypeScript or Python and knowledge of distributed-system failures are expected. Experience with LLM inference, Cloudflare Workers, Postgres, ClickHouse or traffic routing is useful.

How to apply

Review the original posting and apply through the employer’s careers page.

View source and apply Apply directly

Source checked: 2026-10-22

Browse job categories

Python