Jobs

Ollama is seeking a Software Engineer, Cloud to build and scale their cloud inference platform, enabling developers to run open models efficiently. This role involves working on high-throughput, low-latency distributed systems, including inference serving, GPU fleet management, routing, and metering. The ideal candidate will have deep experience with distributed systems, a strong understanding of cost/performance tradeoffs, and familiarity with Kubernetes or GPU scheduling. You will be responsible for designing and owning multi-tenant infrastructure and ensuring the reliability and observability of the platform.