Senior Research Scientist, RL & Post-Training (Hybrid)

DeepL is seeking a Senior Research Scientist to design, implement, and deploy cutting-edge reinforcement learning and post-training research at scale. You will drive innovations that translate to production, collaborating with engineering, ML platforms, and HPC teams.

The role emphasizes building scalable RL pipelines, aligning models with human intent, and advancing safety and efficiency in real-world deployments.