LiteLLM (YC W23): Founding Reliability Engineer – $200K-$270K and 0.5-1.0% equity

3 hours ago

LiteLLM is an open-source AI gateway with 36K+ GitHub stars, routing millions of LLM API calls daily for major companies like NASA, Adobe, Netflix, Stripe, and Nvidia.
The company is seeking its first dedicated reliability hire to ensure production stability, with responsibilities split between operational reliability (60%) and deep performance engineering (40%).
Key challenges include memory management in Python async services, database scalability, and maintaining compatibility across 100+ AI provider APIs.
The role involves owning production reliability, performance engineering, and observability, including on-call duties, incident response, and optimizing hot paths.
Ideal candidates have 2+ years of Python production experience, expertise in async Python, PostgreSQL, Kubernetes, and prior on-call experience.
Strong signals include experience with proxies/API gateways, work at infrastructure companies like Meta or Cloudflare, and contributions to open-source projects.
LiteLLM offers significant scale and impact, open-source visibility, ownership as the first reliability hire, and meaningful equity in a fast-growing startup.

Hasty Briefsbeta