GenAI Research Scientist — LLM Post-Training

Scale AI; Seattle (WA); On-site; USD 166,000 - 207,000; Full time

Benefits offered by this job

Health coverage

Dental coverage

Vision coverage

Retirement plan

Equity compensation

PTO

Job summary

Scale AI is seeking Research Scientists and Research Engineers with expertise in LLM post-training to optimize data curation and evaluation for improving LLMs in text and multimodal modalities. You will develop novel methods to improve alignment and generalization of large-scale generative models and collaborate with researchers to define best practices in data-driven AI development.

The role involves partnering with top labs, publishing findings, and contributing to a broad compensation package

Qualifications

• Ph.D. or Master’s degree in Computer Science, ML, AI, or related field.
• Deep understanding of deep learning, RL, and large-scale model fine-tuning.
• Experience with post-training techniques such as RLHF, preference modeling, or instruction tuning.
• Published research at major conferences or journals.

Responsibilities

• Research and develop novel post-training techniques to enhance LLM capabilities in text and multimodal modalities.
• Design and experiment new approaches to preference optimization.
• Analyze model behavior, identify weaknesses, and propose bias mitigation and robustness solutions.
• Publish research findings in top-tier AI conferences.

Skills

LLM post-training

RLHF

Preference modeling

Instruction tuning

Research publication

Education

Ph.D. or Master’s in CS/ML/AI

Job description

Scale AI is seeking Research Scientists and Research Engineers with expertise in LLM post-training to optimize data curation and evaluation for improving LLMs in text and multimodal modalities. You will develop novel methods to improve alignment and generalization of large-scale generative models and collaborate with researchers to define best practices in data-driven AI development.

The role involves partnering with top labs, publishing findings, and contributing to a broad compensation package