Platform AI Engineer

Role overview Build and operate a platform that lets customers select an AI model and have it deployed automatically on GPU infrastructure from European providers. The role also contributes to training, testing and releasing Dutch language models, with broad responsibility for shaping an early-stage product.

Responsibilities - Develop the model hosting platform, from model selection through GPU allocation and deployment. - Improve service reliability with monitoring, recovery for GPU failures and cost controls. - Support training, evaluation and release of Dutch language models. - Help choose product and engineering priorities in a small team.

Requirements - Experience operating production software, including servers, deployments and troubleshooting. - Backend development experience with PHP and Laravel or Python. - Experience with, or a strong interest in, running AI models on GPUs; familiarity with tools such as vLLM or CUDA is relevant. - Ability to work independently, learn quickly and communicate fluently in English. - Current residence in the Netherlands.

Benefits and work setup - Remote work, with a headquarters in Groningen. - Salary described as competitive and at the top of the market. - Twice-yearly team weeks abroad. - Early-team responsibility and influence over what gets built.