Researcher, Alignment
Core
Designing and implementing scalable solutions to ensure AI systems consistently follow human intent, focusing on robustness, risk measurement, and human-AI interaction paradigms.
Role type
Research Engineer / Research Scientist (AI Alignment)
Builds
Scalable alignment tools, evaluation frameworks, and novel AI research approaches.
Domain
Artificial Intelligence / Machine Learning Safety
Deliverable
production ML models | research
Required skills
Large-scale machine learning system design, alignment algorithms, data visualization, Python, TypeScript, PyTorch
Preferred skills
PhD in CS/Computational Science/Data Science/Cognitive Science, experience with subjective/context-dependent metrics, fast-paced research environments
Technologies
PyTorch, TypeScript, Python
Responsibilities
Develop and evaluate alignment capabilities, design experiments to measure risks and alignment, build tools to study model robustness, design experiments on alignment scaling laws, design Human-AI interaction paradigms, train models for calibration on correctness and risk, design novel approaches for using AI in alignment research
Seniority
Senior, hands-on IC