Research Scientist - FMTA

As a Research Scientist in Foundation Model Task Adaptation at DeepL, you will design, implement, and deploy advanced reinforcement learning algorithms to improve alignment between large language models and human intent. Your responsibilities include building scalable reinforcement learning pipelines, overseeing the entire research lifecycle from concept to production, and collaborating with engineering and ML platform teams to enhance model performance and safety. Additionally, you will foster partnerships with academic and industry experts to advance the impact of your work in Language AI.