Senior AI Researcher: LLM post-training for hallucination reduction (f/m/d)
Core
Design, execute, and scale post-training methodologies (SFT, RL) to eliminate LLM hallucinations and implement uncertainty estimation and self-correction mechanisms.
Role type
Senior AI Researcher (LLM post-training)
Builds
Grounded, reliable LLMs for industrial applications
Domain
Generative AI, Large Language Models, Post-training
Deliverable
production ML models
Required skills
LLM post-training (SFT, RL), distributed training frameworks, Python, PyTorch, uncertainty estimation, calibration, self-consistency, RAG evaluation
Preferred skills
Hallucination mitigation, out-of-distribution detection, claim verification
Technologies
PyTorch, GPU clusters
Responsibilities
Design post-training pipelines, implement uncertainty estimation techniques, benchmark hallucination rates, drive research projects from hypothesis to production
Seniority
Senior, hands-on IC
