Senior AI Researcher: LLM post-training for hallucination reduction (f/m/d)

Highlights

• Train foundation models from scratch with hundreds of GPUs at your disposal.
• Design SFT and RL post-training to eliminate hallucinations and ground models.
• Research uncertainty estimation so models signal when they don't know.

What they offer

• 30 days of paid vacation
• Fitness & wellness offerings via Wellhub
• Mental health support through nilo.health
• Substantially subsidized company pension plan
• Subsidized Germany-wide transportation ticket
• Budget for additional technical equipment
• Flexible working hours and hybrid working model
• JobRad Bike Lease

Ideal candidate

Independent researcher driven by building truthful, reliable AI, excited to own ambitious ideas from hypothesis to production and push grounding and reliability forward.

Requirements

• Hands-on experience fine-tuning or post-training LLMs using distributed training frameworks
• Track record in hallucination mitigation, truthfulness alignment or grounding in RAG
• Experience with uncertainty estimation or out-of-distribution detection
• Experience with RAG evaluation, refusal calibration or claim verification
• Strong programming skills in Python and PyTorch