Scale AI
Machine Learning Research Scientist, Post-Training
$166K–$207K
San Francisco, CA +3 · Full-time · Posted Feb 11, 2025
- Location
- San Francisco, CA
Seattle, WA
New York, NY
San Francisco, California, United States - Education
- Ph.D. or Master's degree in Computer Science, Machine Learning, AI, or a related field.
About the job
Research and develop post-training methods and data strategies to improve the alignment, capabilities, and robustness of text and multimodal large language models.
What you'll do
- Develop post-training techniques such as SFT, RLHF, and reward modeling, and experiment with preference optimization.
- Analyze model behavior, identify weaknesses, and propose ways to mitigate bias and improve robustness.
- Publish research findings and collaborate with researchers, engineers, and foundation model labs on model development.
What they ask for
- 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.
Nice to have
- Published machine learning research at major conferences and/or journals.
- Previous experience in a customer-facing role.
Pay
$165,600 — $207,000 USD (base salary)
Tools
SFT, RLHF
AI focus
Develop post-training, preference optimization, data curation, and evaluation methods to improve LLM alignment, generalization, capabilities, and robustness across text and multimodal modalities.
Model-written summary · the original posting is authoritative