[SocBiN] Postdoc in probabilistic machine learning for evolution and biodiversity

[Fredrik Ronquist]

Postdoctoral researcher in probabilistic machine learning for evolution and biodiversity


The Ronquist lab (https://ronquistlab.github.io<https://ronquistlab.github.io/>) at the Department of Bioinformatics and Genetics, Swedish Museum of Natural History, Stockholm, is looking to hire a postdoctoral researcher in probabilistic programming and probabilistic machine learning for problems in evolution and biodiversity. The lab has a long track record of developing advanced statistical analysis software for phylogenetics, evolution and biodiversity research.

Tasks. You will work within a highly collaborative, interdisciplinary team aiming to develop the next generation of tools for probabilistic inference in evolution and biodiversity. The work is funded by the Swedish Research Council, the Knut and Alice Wallenberg Foundation, and the Swedish Foundation for Strategic Research, among others. The team includes computational biologists, computer scientists and evolutionary biologists at KTH Royal Institute of Technology, BI Norwegian Business School, Université Claude Bernard Lyon 1 and the Swedish Museum of Natural History. The general goal is to separate model specification from the implementation of the inference machinery through universal probabilistic programming (see https://www.nature.com/articles/s42003-021-01753-7). This paves the way for the development of probabilistic machine learning, which extends partially specified models through the application of generative methods to large datasets. The team is in the process of releasing the first version of the TreePPL platform (https://treeppl.org<https://treeppl.org/>), which represents an important first step in this direction. The successful candidate will work with evolutionary biologists and biodiversity researchers in developing and implementing probabilistic models in TreePPL that address challenging scientific problems in areas such as host-parasite evolution, diversification, online tree inference or species circumscription. In particular, we expect the candidate to extend the TreePPL inference machinery to support efficient inference for these models, using novel inference strategies or novel combinations of current techniques like Markov chain Monte Carlo, sequential Monte Carlo, and parallel tempering. We also expect the candidate to extend the framework with generative machine learning capabilities. The work will involve documentation of the platform, teaching at user workshops, and other outreach activities. The project runs until 2026-12-31, and if successful, can be extended further.

Qualifications. We are looking for a candidate with a PhD in a relevant field, such as computational statistics, computer science or bioinformatics. Experience of postdoctoral research would be advantageous. We expect you to have a solid background in and experience of advanced modeling and statistical analysis, including the design or development of new models or inference techniques. We also expect some previous exposure to probabilistic programming and machine learning algorithms. Experience with modeling and analysis of relevant problems, such as inference of phylogeny from genetic data or analysis of environmental DNA data, would be advantageous. Similarly, previous experience with machine learning would be an asset. The work requires excellent skills in written and oral communication in English.
We are looking for a candidate with strong analytical and communicative skills, and who is results-oriented.

For more information contact Professor Fredrik Ronquist (fredrik.ronquist at nrm.se<mailto:fredrik.ronquist at nrm.se>) or Dr Emma Granqvist (emma.granqvist at nrm.se<mailto:emma.granqvist at nrm.se>).

Application deadline: December 3.

Official ad: https://www.nrm.se/ommuseet/jobbahososs/ledigatjanster.9005019.html

Apply here: https://recruit.visma.com/spa/public/apply?guidAssignment=682aeb92-2281-47f7-8af2-985ec9ac694c
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.su.se/pipermail/socbin-at-sbc.su.se/attachments/20231103/8cff3c39/attachment.html>