Machine Learning Engineering Manager
DeepL, London +2
The team
You will lead the Production Inference team — the group responsible for the systems that serve DeepL's language AI models reliably and efficiently at scale. We sit at the intersection of research-grade technical ambition and production-grade operational discipline: our work determines whether DeepL's models reach users with the latency, reliability, and cost profile that makes commercial deployment viable. The team owns the full model serving stack — from GPU-resident inference runtimes and deployment infrastructure through to the developer platform that enables every other research team to bring their models to production.
We operate within the Research organisation, with close ties to DeepL's infrastructure and platform functions, and our architectural decisions affect every product DeepL ships. The broader Research organisation publishes regularly at ACL, NeurIPS, and EMNLP, and the Production Inference team brings that same culture of rigour and innovation to the systems layer of AI.