Site Reliability Engineer, Provider Operations

OpenRouter

. Build and own monitoring for every provider and endpoint, covering latency, throughput, error rates, uptime, and output correctness .

Posted 10/9/2026full-timeRemote • United StatesMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in Site Reliability Engineering (SRE) and production engineering, focusing on observability practices, incident management, and automation of provider operations. Proficient in TypeScript and Python, with a strong understanding of distributed systems and monitoring tools.

Highest-signal resume keywords

Site Reliability Engineering (SRE)Observability PracticesTypeScriptIncident ManagementDistributed Systems

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

MonitoringSLOsError BudgetsLoad TestingAutomationMetricsTracingLogsTraffic ManagementSynthetic Monitoring

Soft Skills

Calm Under PressureClear CommunicationIncident Command

Tools & Technologies

PythonTypeScriptCloudflare WorkersPostgresClickHouseGCPVercel

Industry Keywords

High-Traffic SystemsProvider OperationsAPI GatewayGPU CloudLLM Inference

Tech Stack

Tools & technologies

CloudDistributed SystemsGoogle Cloud PlatformPostgresPythonTypeScript

About the role

Key responsibilities & impact

Build and own monitoring for every provider and endpoint, covering latency, throughput, error rates, uptime, and output correctness
Set SLOs per provider tier and create actionable alerts
Improve detection of degraded endpoints and coordinate automatic traffic failover with the routing team
Own on-call for provider incidents, including triage, mitigation, provider communication, postmortems, and follow-up closure
Create provider scorecards and SLO reporting
Serve as the technical escalation point for misbehaving provider endpoints
Build continuous canaries and evaluations to detect silent quality regressions
Automate provider-operations tasks such as disabling endpoints, capacity changes, deprecations, and rate-limit tuning
Build endpoint load-testing tools for launch readiness and day-zero traffic
Report to the Provider Operations Manager

Requirements

What you’ll need

4+ years in SRE, production engineering, or infrastructure roles running high-traffic, customer-facing systems
Strong observability practice with metrics, tracing, logs, SLOs/error budgets, and actionable alerting
Capable software engineer who prefers writing tools over executing runbooks
Experience with TypeScript and/or Python
Experience with distributed systems failure modes including timeouts, retries, backpressure, and partial outages
Ability to serve as a calm, clear incident commander and communicate with external partners under pressure
Understanding of, or eagerness to learn, LLM inference concepts including streaming, tool calling, prompt caching, throughput/latency tradeoffs, and provider API differences
Experience at an inference provider, model lab, GPU cloud, or API gateway/CDN company is nice to have
Experience with TypeScript, Cloudflare Workers, Postgres, ClickHouse, GCP, or Vercel is nice to have
Background in routing, load balancing, or traffic management systems is nice to have
Experience with evals or synthetic monitoring for ML systems is nice to have