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

The role

You will design, execute, and scale post-training methodologies like SFT and RL to reduce model hallucinations. You will research uncertainty estimation, build distributed fine-tuning pipelines, and design evaluation methods for truthfulness and reasoning accuracy.

What you will do

• Design, execute, and scale post-training methodologies (SFT, RL) to eliminate model hallucinations.
• Research and implement techniques in uncertainty estimation, calibration, self-consistency, and self-correction mechanisms.
• Build and optimize high-throughput, distributed fine-tuning and training pipelines across multi-node GPU clusters.
• Design and implement evaluation methods to benchmark hallucination rates, truthfulness, and reasoning accuracy.
• Drive research projects from initial hypothesis to scalable production implementation and technical reports.

Required qualifications

• Hands-on experience fine-tuning or post-training LLMs using modern distributed training frameworks.
• Track record of research or implementation in at least one of the following domains: Hallucination mitigation / truthfulness alignment / grounding in RAG, Uncertainty estimation, or out-of-distributio
• Strong programming skills (Python & PyTorch).

Benefits

• 30 days of paid vacation
• Access to a variety of 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
• Hybrid working model
• JobRad® Bike Lease

About the company

Aleph Alpha delivers sovereign, human-centric AI to governmental institutions and large enterprises. The organization develops foundational models and next-generation methods for industrial applications.