Hiring: postdoctoral fellows in machine learning for cosmology and astrophysics

We seek outstanding postdoctoral researchers, with background in computational, theoretical and/or observational projects, to develop and deploy cutting-edge machine-learning and AI methods for astrophysics and cosmology, enabling precision tests of fundamental physics with current and next-generation galaxy and time-domain surveys. You will work closely with our teams on the Rubin Observatory ‘s LSST, Euclid, ZTF, and LS4.

 

Image editing: Samuel Avraham.Photo: ESA.

Environment & collaborations

The position is supported by the Excellence Dark Universe Centre And Technology Enabler (EDUCATE), uniting researchers at Stockholm University and KTH Royal Institute of Technology to advance ML for dark matter and dark energy. You will be a member of the Oskar Klein Centre (OKC), a vibrant hub of 100+ researchers in astronomy, astrophysics, cosmology, and particle physics with active programs in dark matter, dark energy, structure formation, transients, and multi-messenger astrophysics.

Postdoctoral researchers at OKC are encouraged and supported to lead visible research projects in major international collaborations and to contribute to the broader scientific community through innovative methodology development, analysis of survey data, and interdisciplinary collaborations.

Postdocs are welcome to participate in Nordita scientific programs, and may join the Aquila Consortium (an international collaboration on ML and data science for cosmic structure; see www.aquila-consortium.org). You will also benefit from our involvement in Learning the Universe (www.learning-the-universe.org), with partners including Columbia University, LBNL, Harvard, Flatiron Institute, Institut d’Astrophysique de Paris, Université de Montréal, Princeton, Carnegie Mellon, and MPA Garching.

Main responsibilities

  • Field-level inference and simulation-based inference for cosmology
  • Neural emulators / surrogate models for accelerated forward modelin
  • Differentiable simulations and probabilistic programming for end-to-end pipelines
  • Robust uncertainty quantification, systematics mitigation, and domain adaptation
  • ML for time-domain discovery and characterization (e.g., transients, time-delay cosmography)

Application and more information regarding the position

Last updated: September 24, 2025

Source: Oskar Klein Centre

eventNewsArticle

standard-article

false

{
  "dimensions": [
    {
      "id": "department.categorydimension.subject",
      "name": "Global categories",
      "enumerable": true,
      "entities": [],
      "localizations": {}
    },
    {
      "id": "department.categorydimension.tag.Keywords",
      "name": "Keywords",
      "enumerable": false,
      "entities": [],
      "localizations": {}
    },
    {
      "id": "department.categorydimension.tag.Person",
      "name": "Person",
      "enumerable": false,
      "entities": [],
      "localizations": {}
    },
    {
      "id": "department.categorydimension.tag.Tag",
      "name": "Tag",
      "enumerable": false,
      "entities": [],
      "localizations": {}
    },
    {
      "id": "webb2021.categorydimension.Category",
      "name": "News Category (Webb 2021)",
      "enumerable": true,
      "entities": [],
      "localizations": {}
    },
    {
      "id": "webb2021.categorydimension.Label",
      "name": "Etiketter (Webb 2021)",
      "enumerable": true,
      "entities": [],
      "localizations": {}
    },
    {
      "id": "webb2021.categorydimension.Label.en",
      "name": "Labels (Webb 2021)",
      "enumerable": true,
      "entities": [],
      "localizations": {}
    },
    {
      "id": "webb2021.categorydimension.Keyword",
      "name": "Keywords (Webb 2021)",
      "enumerable": false,
      "entities": [],
      "localizations": {}
    }
  ]
}