SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
OpenRouter is the leading AI routing and infrastructure layer that enterprises use to access, manage, and optimize large language models across providers without lock-in or unnecessary cost. The company powers advanced AI teams by providing flexibility to move fast, scale confidently, and stay future-proof as models evolve.
The Provider Ecosystem team owns the supply side of OpenRouter: every model, endpoint, and provider the router can send requests to. This includes hundreds of providers, thousands of endpoints, and millions of requests daily in a rapidly evolving model landscape.
As Engineering Manager for this team, you will report to the VP of Engineering and lead a hands-on technical team at the front of the AI infrastructure industry. Labs and inference providers actively seek to reach OpenRouter's users, giving this team early access to novel inference offerings, often through exclusive and stealth launches.
Key responsibilities include:
- Leading the team: hiring and growing strong engineers, setting roadmap, staying hands-on in code reviews and incidents, and advocating for the team with leadership
- Owning provider adapters, endpoint lifecycle, and routing logic; serving as technical counterpart for top providers; running day-zero and stealth launches; coordinating with GTM, BD, and legal to move providers from signed NDA to live in weeks
- Leading expansion beyond text into image, video, audio, embeddings, plus realtime and batch inference
- Owning evals and inference quality benchmarks, turning data into routing decisions and direct feedback to improve providers
This is a hands-on leadership role where you'll stay deep in the code, lead by example, and be OpenRouter's technical face to partner labs and providers.
REQUIREMENTS:
- 4+ years of engineering management experience, including at least one environment where you built or scaled a team during rapid growth
- Strong technical foundation in distributed systems, API design, and LLM inference; understanding of how inference is served (streaming, tool calling, prompt caching, quantization, throughput/latency trade-offs), how provider APIs differ, and routing millions of requests across heterogeneous endpoints
- Hands-on and comfortable staying that way; you write code, use AI-assisted development tools, and lead by example
- Externally facing capability; can negotiate integrations with model labs' engineering teams and represent OpenRouter's technical requirements independently
- Data-driven approach to quality; preference for benchmarks, evals, and production telemetry over intuition
- Proven ability to recruit and retain strong engineers; ideally with a network of talent
- High agency and clear communication; you identify what matters, make plans, drive them forward, and speak up with substance when disagreeing
- Pragmatic about lean engineering org needs; optimize for speed and clarity over process
NICE TO HAVES:
- Experience at an inference provider, model lab, GPU cloud, or building products on top of many LLM APIs
- Experience with TypeScript, Cloudflare Workers, Postgres, ClickHouse, GCP, or Vercel
- Background in evals, benchmarking, or routing/load-balancing systems
- Experience shipping multimodal APIs or realtime/batch inference
- Experience running vendor security and compliance reviews (NDA, DPA, SOC 2)
- Existing OpenRouter user or active side projects in AI infrastructure or developer tooling
