Generative AI Research Scientist: LLM Post-Training

Scale AI, Inc. is seeking Research Scientists and Research Engineers with expertise in LLM post-training (SFT, RLHF, reward modeling) to optimize data curation and evaluation for improved LLM capabilities in text and multimodal modalities.

You will develop novel methods and collaborate with leading labs to influence the next generation of generative AI. The role emphasizes rigorous research, experimentation with bias mitigation, and dissemination of findings at major conferences and journals.