Postdoctoral Researcher in Optimization

Job Summary

Seeking a full-time Postdoctoral Researcher in Optimization, this role focuses on developing optimization and sampling methods for cross-scale scientific applications, leveraging models trained on heterogeneous evidence to improve experimental design and model predictions.

Key responsibilities

• Develop optimization and sampling strategies to determine experimental conditions and measurements for enhancing model predictions
• Implement original methodologies in numerical optimization, Bayesian optimization, and adaptive experimental design
• Address challenges related to noisy, sparse data and uncertainty in models while collaborating with multidisciplinary teams

Required qualifications

• Recent PhD graduate within the last three years
• Experience in optimal experimental design strategies and selecting experiments to maximize information
• Demonstrated expertise in active learning and sequential design methods
• Familiarity with Bayesian optimization and development of acquisition functions and surrogate models
• Understanding of information theory and decision theory related to uncertainty reduction and practical decisions