Teams at Ollama Inc.

Own Ollama’s developer relations strategy and execution by engaging developer communities, partnering with model labs and hardware companies, creating technical content, gathering user feedback, and delivering demos at meetups and conferences. The role combines hands-on engineering with public-facing communication, including code, tutorials, technical blog posts, videos, and social content built around open models.

Build and refine Ollama’s desktop app, CLI, onboarding, APIs, and integrations with developer tools and agent harnesses. Develop native, backend, and web systems supporting local and cloud models, test complete user workflows, improve compatibility, and partner with model and inference engineers to ship reliable product experiences.

Build and scale Ollama’s cloud inference platform, including high-throughput serving, GPU and regional workload routing, multi-tenant infrastructure, quotas, metering, billing, tiering, reliability, observability, and cost controls. The role requires production ownership of distributed systems and familiarity with Kubernetes, GPU scheduling, inference infrastructure, reliability practices, SLOs, and capacity planning.