Senior AI Researcher LLM Post Training for Hallucination Reduction

You will research, develop, and scale LLM post-training methods, including supervised fine-tuning and reinforcement learning, to reduce hallucinations and ground model outputs in evidence. You will implement uncertainty, calibration, self-consistency, and self-correction techniques; build distributed GPU training pipelines; create evaluation benchmarks; and independently take research projects from hypotheses through production implementation and technical reports.

Responsibilities

• Design, execute, and scale LLM post-training methodologies to reduce hallucinations and improve evidence grounding
• Research and implement uncertainty estimation, calibration, self-consistency, and self-correction mechanisms
• Build and optimize distributed fine-tuning and training pipelines across multi-node GPU clusters
• Design and implement evaluation methods for hallucination rates, truthfulness, and reasoning accuracy
• Drive research projects from hypothesis through scalable production implementation and technical reporting

Requirements

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

Benefits

• 30 days of paid vacation
• Fitness and wellness offerings through Wellhub
• Mental health support through nilo.health
• Subsidized company pension plan
• Subsidized Germany-wide transportation ticket
• Budget for additional technical equipment
• Flexible working hours
• Hybrid working model
• JobRad bike lease