Tech Stack

Description

You will develop and evaluate probabilistic inference methods, focusing on amortized inference, and translate theoretical insights into practical implementations for safe-by-design AI systems.

Requirements

• Advanced degree in relevant field (PhD preferred)
• Minimum 3 years deep learning research experience
• Expertise in probabilistic inference and at least one of: Bayesian inference, amortized inference, RL, optimal control
• Strong mathematics background
• Proficiency in Python and ML frameworks (PyTorch or TensorFlow)

Responsibilities

• Develop amortized inference methods for high-dimensional discrete and continuous distributions
• Develop parameter- and structure-learning methods for large probabilistic graphical models
• Design evaluation strategies for methods relying on probabilistic inference
• Collaborate with mathematicians on learning and inference theory
• Translate theoretical proposals into high-quality Python implementations