Description
Trezor is hiring an AI Platform Engineer to own a dedicated multi-GPU server and its AI inference infrastructure end to end. The role covers the server’s operating system, storage, networking, observability, alerting, model-serving stacks, open-weight model deployment and benchmarking, quotas and usage reporting, and support for developers integrating models into tools. Candidates should have coding and infrastructure-as-code experience, Linux systems administration knowledge, and an interest in the open-weight model ecosystem; production LLM-serving, NVIDIA GPU, datacenter, and model-evaluation experience are preferred.
