Develop novel methods for uncertainty quantification in deep learning; Work with state-of-the-art neural network architectures applied to molecular data; Publish scientific papers and present research results in top machine learning conferences such as NeurIPS, ICML, UAI, and AISTATS; Contribute to supervision and management within the research project
Requirements:
As a formal qualification, you must hold a PhD degree (or equivalent); Proven experience in Bayesian methods, probabilistic modeling, and probability theory; Proven experience with implementing machine learning methods in Python and Pytorch/Tensorflow; A strong publication record within uncertainty quantification, Bayesian neural networks, graph neural networks, machine learning-based molecular discovery, diffusion-based generative models, or other related fields
Text:
Postdoc in Machine Learning: Uncertainty Quantification in Graph Neural Networks Develop novel methods for uncertainty quantification in deep learning; Work with state-of-the-art neural network architectures applied to molecular data; Publish scientific papers and present research results in top machine learning conferences such as NeurIPS, ICML, UAI, and AISTATS; Contribute to supervision and management within the research project As a formal qualification, you must hold a PhD degree (or equivalent); Proven experience in Bayesian methods, probabilistic modeling, and probability theory; Proven experience with implementing machine learning methods in Python and Pytorch/Tensorflow; A strong publication record within uncertainty quantification, Bayesian neural networks, graph neural networks, machine learning-based molecular discovery, diffusion-based generative models, or other related fields
Please click here, if the job didn't load correctly.
Please wait. You are being redirected to the job in 1 seconds.
