Research Manager | Production Inference

DeepL is looking for a Research Manager to lead its Production Inference team, which owns the systems that serve DeepL's language AI models reliably and efficiently at scale, including GPU-resident inference runtimes, deployment infrastructure, and the developer platform used by other research teams. This is a people-leadership and technical-direction role rather than hands-on coding, involving technical reviews, architecture decisions, and research direction for the inference stack. The manager will own the team's roadmap for production inference systems, act as the primary technical interface with adjacent research and infrastructure teams, and drive reliability, efficiency, and cost performance of the model serving stack. The role is based in London.