Ollama
Software Engineer, Runtime
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
- Make open models run fast and reliably on everything from a MacBook to server GPUs.
- Own parts of the runtime: model loading, memory, quantisation and GPU backends.
- Get new model families and formats working on day one, and cut start-up time and time to first token.
- Work with model labs and chip makers, in the open. Based in Palo Alto.
Example projects: halve a popular model's cold start; run a 70B model on one consumer GPU; add a new GPU backend.
What they look for
- Strong systems skills in Go, C or C++.
- Has worked close to the hardware: GPUs, inference, game engines, databases or operating systems.
- Has profiled and sped up real workloads.
- Comfortable shipping to millions of users on every kind of machine.
Helpful: quantisation; CUDA, Metal or MLX.
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.
