Machine Learning Research Scientist, Post-training

Scale AI Scale AI · Data AI · San Francisco, CA · Research

Research Scientist focused on LLM post-training techniques (SFT, RLHF, reward modeling) to enhance text and multimodal capabilities. Involves optimizing data curation, analyzing model behavior, and publishing findings.

What you'd actually do

  1. Research and develop novel post-training techniques, including SFT, RLHF, and reward modeling, to enhance LLM core capabilities in both text and multimodal modalities.
  2. Design and experiment new approaches to preference optimization.
  3. Analyze model behavior, identify weaknesses, and propose solutions for bias mitigation and model robustness.
  4. Publish research findings in top-tier AI conferences.

Skills

Required

  • 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

Nice to have

  • Previous experience in a customer facing role.

What the JD emphasized

  • novel methods
  • post-training
  • RLHF
  • reward modeling
  • multimodal
  • preference optimization
  • model behavior
  • bias mitigation
  • model robustness
  • Published research

Other signals

  • LLM post-training
  • optimizing data curation and eval
  • enhance LLM capabilities
  • novel methods to improve alignment and generalization
  • partner with top foundation model labs