---
title: 'Site Reliability Engineer, Provider Operations at OpenRouter'
canonical: 'https://feeny.ai/job/site-reliability-engineer-provider-operations-openrouter-united-states-j18dk08e73e4'
type: 'job'
last_seen: '2026-10-17'
---

# Site Reliability Engineer, Provider Operations at OpenRouter

- **Company:** OpenRouter
- **Location:** United States
- **Employment:** full-time
- **Work type:** remote
- **Posted:** 2026-10-13
- **Last confirmed live:** 2026-10-17
- **Apply:** https://jobs.ashbyhq.com/openrouter/78fc4670-5ba0-4146-b8b1-1ef4d91b96f1

## Job description

## About OpenRouter

OpenRouter is the leading AI routing and infrastructure layer that enterprises use to access, manage, and optimize the best large language models across providers—without lock-in, capacity constraints, or unnecessary cost. We power the most advanced AI teams in the world by giving them the flexibility to move fast, scale confidently, and stay future-proof as models evolve.

As enterprise adoption of AI accelerates, OpenRouter sits at the center of how organizations operationalize LLMs across research, product, and production workloads.

## About the Role

OpenRouter routes almost a billion requests and more than 20 trillion tokens a day, across 80+ providers and thousands of endpoints. Every one of those providers can degrade, rate-limit, change behavior, or go down without warning. Our customers count on us to absorb that chaos so their apps never notice. We're hiring our first AI Inference SRE to own the operational health of our provider supply. You'll make sure every endpoint we route to is fast, correct, and available, and that we detect and route around problems before customers do. You'll sit on the Provider Operations team, reporting to the Provider Operations Manager.

## What You'll Do

- Provider health and observability. Build and own monitoring for every provider and endpoint: latency, throughput, error rates, uptime, and output correctness. Set SLOs per provider tier and alert on them.
- Detection and failover. Improve how quickly we detect degraded endpoints, and work with the routing team so traffic shifts away from them automatically.
- Incident response. Own on-call for provider incidents: triage, mitigate, communicate with providers, run postmortems, and drive follow-ups to closure.
- Provider accountability. Turn telemetry into scorecards and SLO reporting that providers act on, and be the technical escalation point when a provider's endpoint is misbehaving.
- Quality regression detection. Build continuous canaries and evals that catch silent regressions (quantization changes, broken tool calling, truncated streams, pricing or usage-reporting mismatches), not just outright downtime.
- Automate the toil. Replace manual provider-ops work (disabling endpoints, capacity changes, deprecations, rate-limit tuning) with safe, auditable tooling.
- Capacity and launch readiness. Build tooling to load-test endpoints before big launches so day-zero traffic doesn't take them down.

## About You

- 4+ years in SRE, production engineering, or infrastructure roles running high-traffic, customer-facing systems.
- Strong with observability tooling and practice: metrics, tracing, logs, SLOs/error budgets, alerting that is always actionable.
- Capable software engineer who prefers writing tools over executing runbooks. TypeScript and/or Python.
- Experienced with distributed systems failure modes: timeouts, retries, backpressure, partial outages, noisy neighbors.
- Calm, clear incident commander who communicates well with external partners under pressure.
- Understands, or is eager to learn deeply, how LLM inference is served: streaming, tool calling, prompt caching, throughput/latency tradeoffs, and how provider APIs differ.

## Nice to Have

- Experience at an inference provider, model lab, GPU cloud, or API gateway/CDN company.
- Experience with our stack: TypeScript, Cloudflare Workers, Postgres, ClickHouse, GCP, Vercel.
- Background in routing, load balancing, or traffic management systems.
- Experience with evals or synthetic monitoring for ML systems.

## About OpenRouter

## Company Overview
- **One-liner**: OpenRouter provides a unified API that gives developers access to 400+ large language models from 70+ providers through a single interface.
- **Entity Type**: Private (Series B)
- **Headquarters**: New York, New York, United States
- **Founded**: 2023
- **Founders**: Alex Atallah (CEO, Co-Founder), Louis Vichy (Co-Founder)

## Core Business
- **Primary industry**: AI Infrastructure / Developer Tools
- **Target customers**: B2B — software developers, AI application builders, and enterprises building agentic and LLM-powered products.
- **Mission or purpose**: To be the unified interface for LLMs, helping developers build AI applications without worrying about provider lock-in, downtime, or complex integrations.

## Products & Services
- **Unified LLM API**: A single, OpenAI-compatible API endpoint that provides access to 400+ models from 70+ providers (OpenAI, Anthropic, Google, Meta, Mistral, etc.). Handles authentication, request routing, rate limiting, and automatic failover. Developers avoid managing separate API keys and billing relationships.
- **Enterprise Offering**: Custom data policies, fine-grained provider controls, and dedicated support for organizations that need data governance and compliance.
- **Model & App Rankings**: A public leaderboard and community hub for discovering top-performing models and AI applications built on the platform.

## Market Standing
- **Valuation**: Not publicly disclosed.
- **Key Metric**: Total funding of **$200M** across multiple rounds (Seed, Series A, Series B).
- **Latest Funding**: $120M venture round in April 2026.
- **Notable Investors**: Andreessen Horowitz, Menlo Ventures, Snowflake Ventures, ServiceNow Ventures, League of Generalists.
- **Growth Signals**: Processes **100 trillion tokens monthly**; serves **250k+ apps** and **4.2M+ global users**; headcount grew **+611% year-over-year** to 46 employees; LinkedIn followers grew **+871.9% year-over-year** to 14,754.

## Competitive Advantages
- **Provider Agnosticism**: Developers are not locked into a single provider; OpenRouter handles failover and routing across 70+ providers, ensuring high availability and resilience.
- **Cost Optimization**: Offers better prices than going direct to many providers, with no subscription fees — users simply buy credits.
- **Massive Model Selection**: 400+ models in one API, from frontier reasoning models to lightweight, cost-optimized options, enabling dynamic model selection per task.
- **OpenAI-Compatible SDK**: Drop-in replacement for existing OpenAI integrations, minimizing migration friction.

## Strategic Focus
- **Scaling Infrastructure**: Building distributed inference infrastructure to improve reliability and reduce latency for global users.
- **Enterprise Adoption**: Growing enterprise sales team and launching dedicated enterprise features (data policies, compliance controls).
- **Agentic Development**: Supporting the next wave of autonomous AI agents with robust routing, fallback, and observability.
- **Platform Expansion**: Growing the ecosystem of featured agents and apps built on OpenRouter.

## Why Work Here
- **Remote First**: Flexibility to work from anywhere in the US.
- **Small, High-Impact Team**: ~46 employees with a flat structure where every person has direct impact on the product and users.
- **Competitive Compensation**: Top-of-market salary and equity packages.
- **Health & Wellness**: Fully covered health, dental, and vision plans for you and your dependents.
- **WFH Budget**: Annual stipend for home office setup and internet.
- **Unlimited PTO**: Encouraged time off to recharge.
- **Quarterly Offsites**: Regular team gatherings to connect in person.
- **Engineering Culture**: High ownership, small team punching above its weight, building critical AI infrastructure at massive scale (100T tokens/month).

## Strategic Focus
- **Scaling Infrastructure**: Building distributed inference routing to improve reliability and reduce latency globally.
- **Enterprise Growth**: Expanding enterprise sales, security, and compliance features to serve larger organizations.
- **Agentic Ecosystem**: Supporting the next wave of autonomous AI agents with robust routing, fallback, and observability.
- **Platform Expansion**: Growing the marketplace of featured agents and apps, and deepening integrations with developer tools.

## Competitive Advantages
- **Provider Agnosticism**: Developers are not locked into a single provider; OpenRouter handles failover and routing across 70+ providers, ensuring high availability.
- **Cost Optimization**: Offers better prices than going direct to many providers, with no subscription fees — users simply buy credits.
- **Massive Model Selection**: 400+ models in one API, from frontier reasoning models to lightweight, cost-optimized options.
- **OpenAI-Compatible SDK**: Drop-in replacement for existing OpenAI integrations, minimizing migration friction.

## Why Work Here
- **Remote First**: Flexibility to work from anywhere in the US.
- **High Impact, Small Team**: ~46 employees, each with direct impact on the product and millions of users.
- **Competitive Compensation**: Top-of-market salary and equity packages.
- **Health & Wellness**: Fully covered health, dental, and vision plans for you and your dependents.
- **WFH Budget**: Annual stipend for home office setup and internet.
- **Unlimited PTO**: Encouraged time off to recharge.
- **Quarterly Offsites**: Regular team gatherings to connect in person.
- **Engineering Culture**: High ownership, small team punching above its weight, building critical AI infrastructure at massive scale.

## Sources
1. [openrouter.ai](https://openrouter.ai/)
2. [openrouter.ai/careers](https://openrouter.ai/careers)
3. [jobs.ashbyhq.com/openrouter](https://jobs.ashbyhq.com/openrouter/)
4. [cbinsights.com](https://www.cbinsights.com/company/openrouter)
5. [linkedin.com/company/openrouter](https://www.linkedin.com/company/openrouter)

## Other roles at OpenRouter

- [Customer Engineer, APAC](https://feeny.ai/job/customer-engineer-apac-openrouter-apac-1mra2rf7fwfw) — APAC
- [Business Development Representative, Enterprise](https://feeny.ai/job/business-development-representative-enterprise-openrouter-united-states-r9ksdb1qmwtj) — United States
- [IT Manager](https://feeny.ai/job/it-manager-openrouter-new-york-h4f8zd8xr9bm) — New York, NY
- [Software Engineer, Ori](https://feeny.ai/job/software-engineer-ori-openrouter-united-states-hhnpazwg5tmq) — United States
- [Product Marketing Manager, Enterprise](https://feeny.ai/job/product-marketing-manager-enterprise-openrouter-united-states-2q95fjg7keq8) — United States
- [Product Manager, OpenRouter Connect](https://feeny.ai/job/product-manager-openrouter-connect-openrouter-united-states-528m22mvv1h8) — United States
- [GRC Manager](https://feeny.ai/job/grc-manager-openrouter-united-states-72y537rhzzyq) — United States
- [Engineering Manager, Provider Ecosystem](https://feeny.ai/job/engineering-manager-provider-ecosystem-openrouter-united-states-gyn2ks85jeq4) — United States
- [Software Engineer, Trust & Safety](https://feeny.ai/job/software-engineer-trust-safety-openrouter-united-states-5hgj3pzc4aa4) — United States
- [Solutions Architect](https://feeny.ai/job/solutions-architect-openrouter-united-states-qr713fthv7qn) — United States