jobs

Senior AI Researcher- Reinforcement learning (f/m/d)

Aleph Alpha is seeking a Senior AI Researcher specializing in reinforcement learning to join its post-training team in Heidelberg, Germany, with hybrid working available in Germany. The role focuses on improving the reinforcement-learning m

In inglese

Company

Aleph Alpha

Location

Heidelberg, Germany

Status

Closed

Posted

2026-09-19T03:35:29.822+00:00

Aleph Alpha's post-training team in Heidelberg is hiring a senior researcher to improve the reinforcement-learning methods behind its large language models, which feed into customer-facing models. The job mixes theory and engineering: large-scale RL experiments, analysing evaluations, scaling distributed training, optimising RL loops, and developing multi-turn RL approaches. It asks for deep RL theory, multi-node LLM training experience, Python and PyTorch distributed, and statistical evaluation skills; a PhD or equivalent research experience and NeurIPS, ICML or ICLR publications are preferred. Relocation to Heidelberg or regular travel is required.