Ollama
Software Engineer, Cloud
The most popular free way to run AI models on your own computer — you install one app, type one command, and a model runs on your machine with nothing leaving…
Palo AltoFull-time
Checked 22 Nov
What you’d do
- Build and scale the platform that serves every model request on ollama.com.
- Design the routing that places work across GPUs and regions for cost, speed and uptime.
- Own the shared infrastructure: isolation, quotas, usage metering, billing and plan tiers.
- Build reliability, monitoring and cost controls. Based in Palo Alto.
What they look for
- Deep experience with fast, high-volume distributed systems such as inference serving or traffic routing.
- Has owned a production service and made cost and speed trade-offs at scale.
- Kubernetes, GPU scheduling or inference infrastructure.
- Thinks in SLOs and honest capacity planning.
Helpful: built an inference platform, managed a GPU fleet, or built metering for an AI service.
Know the company before you applyFull company page →
- funding, as the company states it
- Series B
Ollama hires through MenFem. How, and what that means for our review, is on the company page.
