Scale works with the industry’s leading AI labs to provide high quality data and accelerate progress in GenAI research. We are looking for Research Scientists and Research Engineers with expertise in LLM post-training (SFT, RLHF, reward modeling). This role will focus on optimizing data curation and algorithmic improvements to enhance LLM capabilities in core areas such as instruction following, factuality, coding, multilingual and multimodal understanding.
In this role, you will develop novel methods to improve the alignment and generalization of large-scale generative models. You will collaborate with researchers and engineers to define best practices in data-driven AI development. You will also partner with top foundation model labs to provide both technical and strategic input on the development of the next generation of generative AI models.
You will:
- Research and develop novel post-training techniques, including SFT, RLHF, and reward modeling, to enhance LLM core capabilities in areas of instruction following, factuality, coding, multilingual and multimodal understanding.
- Design and experiment new approaches to preference optimization.
- Analyze model behavior, identify weaknesses, and propose solutions for bias mitigation and model robustness.
- Publish research findings in top-tier AI conferences.
Ideally you’d have:
- Ph.D. or Master's degree in Computer Science, Machine Learning, AI, or a related field.
- Deep understanding of deep learning, reinforcement learning, and large-scale model fine-tuning.
- Experience with post-training techniques such as RLHF, preference modeling, or instruction tuning.
- Excellent written and verbal communication skills
- Published research in areas of machine learning at major conferences (NeurIPS, ICML, ICLR, ACL, EMNLP, CVPR, etc.) and/or journals
- Previous experience in a customer facing role.
