Machine Learning Research Scientist, Post-Training

Company

Scale AI develops reliable AI systems, providing high-quality data and full-stack technologies for leading AI models and enterprise and government applications.

What you will do

• Research and develop post-training techniques including supervised fine-tuning, RLHF, and reward modeling for large-scale generative models.
• Improve LLM capabilities across text and multimodal modalities.
• Design and experiment with preference optimization approaches.
• Analyze model behavior, identify weaknesses, and develop solutions for bias mitigation and model robustness.
• Collaborate with researchers and engineers to define best practices for data-driven AI development.
• Publish research findings at leading AI conferences.

Requirements

• 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 RLHF, preference modeling, instruction tuning, or related post-training techniques.
• Excellent written and verbal communication skills.
• Published machine learning research in major conferences or journals.
• Previous experience in a customer-facing role.

Culture & Benefits

• Comprehensive health, dental, and vision coverage.
• Retirement benefits and generous paid time off.
• Learning and development stipend.
• Eligible roles may include equity compensation and a commuter stipend.
• Inclusive equal opportunity workplace with reasonable accommodations for applicants with disabilities.