Sort by
Refine Your Search
-
Listed
-
Country
-
Employer
- University of Oslo
- ;
- AbbVie
- Auburn University
- Harvard University
- Korea Institute for Advanced Study
- Nanyang Technological University
- University of British Columbia
- Wayne State University
- Genentech
- LINGNAN UNIVERSITY
- Marquette University
- NTNU - Norwegian University of Science and Technology
- Nature Careers
- Northeastern University
- SciLifeLab
- The University of Alabama
- The University of Queensland
- The University of Western Australia
- University of Alabama, Tuscaloosa
- University of Bergen
- University of Liverpool
- University of San Francisco
- University of Texas at Austin
- University of Waterloo
- Western Norway University of Applied Sciences
- Zintellect
- 17 more »
- « less
-
Field
-
Jhunjhunwala Lab at Genentech, please go to: https://www.gene.com/scientists/our-scientists/suchit-jhunjhunwala Relevant publications: Thrift, W. J. et al. Graph-pMHC: graph neural network approach to MHC class
-
-generation digital workflows — including methods for knowledge graph construction, advanced querying, and data quality assurance. Contribute to aligning the developed methods with emerging standards
-
, energy, geoscience). Explore the combination of Generative AI, logic-based models, and systems engineering principles to support next-generation digital workflows — including methods for knowledge graph
-
HiPerBreedSim project. In this role, you will leverage recent advances in working with ancestral recombination graphs (ARGs) to develop algorithms and code for simulating population genomic data, including
-
. Research areas include Representation Learning, Machine learning and Optimization on graphs and manifolds, as well as applications of geometric methods in the Sciences. This is a one-year position with
-
regarding research results. Preferred Qualifications: Experience with deep/graph neural networks and active involvement in data science and machine learning projects. Experience in multimodal data fusion (e.g
-
representation methods for accelerated inverse design Large language, diffusion & graph neural models for materials discovery Fine tuning and architecture optimisation of foundation models Inverse design of next
-
Responsibilities: Conduct programming and software development for graph data management. Design and implement machine learning models for optimizing graph data management. Conduct experiments and evaluations
-
available for two years. Keywords: Geometric Deep Learning, in particular Graph Neural Networks, Deep Reinforcement Learning, Generative Modelling, in particular Denoising Diffusions, Combinatorial
-
Learning, in particular Graph Neural Networks, Deep Reinforcement Learning, Generative Modelling, in particular Denoising Diffusions, Combinatorial Optimisation Commitment to Diversity The University