Prof. Gianni De Fabritiis, ICREA research professor at the Computational Science Laboratory,  University Pompeu Fabra, Barcelona

I am looking for a Postdoctoral researcher to join our laboratory in Barcelona for a two years project focused on constructing molecular representations of chemical space to be used for property prediction and generative modeling. We expect to use semi-supervised approaches, diffusion models as well as equivariant representations of molecules (e.g. TorchMD-NET). The project is in collaboration with a pharmaceutical company and will have access to private datasets. 

What you will do

• Implementing state-of-the-art deep neural architecture for molecular representation (e.g. TorchMD-NET) in pytorch

• Build foundation models of three-dimensional molecular structures using unsupervised learning approaches from which specific downstream tasks can be trained in a supervised and data-efficient manner

• Integration of conformational flexibility into the model

• Develop a generative model which is dependent on structural information to propose new molecules

What you need

• The candidate will have a PhD in computer science, physics, chemistry,  or a similar discipline.

• Excellent knowledge of at least a machine learning framework, preferably PyTorch or Jax, and Python.

• We seek exceptional candidates with a passion for using computation and machine learning to solve real problems.

• Experience in previous machine learning projects is a requirement.

• The capability to think out of the box, the ambition to work on very innovative projects, and very good communication skills in English.

• Excellent publication record.

Location

The laboratory is located in the Barcelona Biomedical Research Park (PRBB) which, with a privileged location on the shoreline of the Mediterranean sea, constitutes one of the most exciting interdisciplinary research centers in Southern Europe with more than 1000 scientists in the building alone. The PRBB is more than just a research institution, it is a unique creative space that connects science and diversity. By becoming a member of its research community, the candidate will have access to conferences, networking opportunities, and training events.

Facilities

Access to state-of-the-art computational resources and large amounts of simulation data will be crucial for the development and validation of novel computational protocols. The lab is equipped with a cluster with state-of-the-art GPUs and has exclusive access to GPUGRID.net, a distributed computing project with 5000 GPUs.

Offer

We offer a position for up to two years and a competitive salary for similar positions in Barcelona. 

Start date

Anytime from now.

To apply

Please send an email to gianni.defabritiis@upf.edu with the subject “PD202211” with a CV and a cover letter together with the names of up to three contacts for references. We will contact you only if you are selected for the interview.