jobs
Senior AI Researcher: LLM post-training for hallucination reduction (f/m/d)
Aleph Alpha is seeking a senior AI researcher for its hallucination-reduction capability team. The role focuses on improving large language model post-training, especially supervised fine-tuning and…
In inglese
- Company
- Aleph Alpha
- Location
- Heidelberg, Germany
- Status
- Closed
- Posted
- 2026-10-16 03:36 UTC
Senior AI researcher role in Aleph Alpha’s hallucination-reduction capability team, based in Heidelberg with hybrid work. The person designs and scales post-training methods, including supervised fine-tuning and reinforcement learning, to make language models ground answers in evidence and signal uncertainty. Work covers uncertainty estimation, calibration, self-consistency, self-correction, distributed fine-tuning on multi-node GPU clusters, and evaluations of hallucination rates, truthfulness and reasoning accuracy. The posting asks for hands-on LLM fine-tuning experience, strong Python and PyTorch, and research ownership from hypothesis through implementation and reporting.
Original job posting