Sano Postdoc

Embedding explainability in AI machine learning process

Give us a chance to meet you

Sano Centre for Computational Medicine is a new International Scientific Foundation located in Kraków, Poland.

Sano aspires to be a major translational scientific institute, operating at the meeting point of academic science, established MedTech industry, and emerging start-up environment, combining the best of these three perspectives.

Sano acts as a core technology and expertise provider for industry, and creator of innovation, developing state-of-the-art solutions for healthcare. Thanks to the substantial funding and excellent European partnership network, Sano will bring a critical mass to this transformational field of research, in order to translate scientific advancements onto clinical practice. Sano’s ambition is to become the Reference Centre for Computational Medicine in Central Europe and build a reputation as a leading institute on a global level.

As a cross-disciplinary institution, Sano uses machine learning/artificial intelligence (ML/AI), large scale computer simulations (HPC), data science, and other computational technologies towards overcoming global challenges in healthcare systems. The research agenda will be executed in close collaboration with Partners in Poland, EU and USA.

We value:

  • Passion – Passion in what we do, engagement in Sano operations, taking responsibility, providing initiative, being happy at work.
  • Innovation – Boldness in articulating and pursuing novel ideas, courage to think outside the box.
  • Integrity – Directness, openness, tolerance and respect. Scientific integrity (we do not cut corners).
  • Diversity – Diversity in backgrounds, cultures and opinions of Sano employees. Promotion of women in STEM.

Machine learning algorithms are becoming, or already are, an essential part of the human decision-making processes. As a result of their increasing impact on human daily lives, the problem of the so-called trustworthy artificial intelligence (AI), becomes fundamental. This is of particular importance when developing AI machine learning process for medical purposes. One of the fundamental elements of trustworthy AI should be its ability to explain the assumptions applicable to the obtained results.  The research that is proposed here is a one-year research project where knowledge from theoretical physics, from the field of statistical physics, it will be explored as an avenue to embed explainability in the machine learning process to support a trustworthy AI. It will be integrated in AI the conceptual framework being developed in the Personal Health Data Science Group.

It’s possible that the explainability of an algorithm can be ensured by embedding it with an archetypical model from statistical physics.  The form of such a model is strongly dependent on the representation of knowledge and data used in the problem.  In the case of knowledge graph representation, such a model should be based on well-known statistical physics network models, such as the ISING model. Such a description should automate the identification of the interdependences between different knowledge elements associated with data features and to analyse them qualitatively and quantitatively. A model constructed in this way will allow not only to prospect pathways, but also to trace the features affecting it. Moreover, thanks to the description of the interdependences, a statistical physics-based model of knowledge graphs may also prospect the further evolution of the system and identify system elements whose change can reverse the disorderly changes of the system. The implementation of this plan is strongly related to the overall project carried out by the research group. Preparations will require proper presentation of data, simplification by means of abstraction and determination of dynamic methods for determining the links between them.

You are expected to:

  • do original research under the direction of one of Research Group Leaders;
  • publish your work in peer-review journals and present during national and international conferences;
  • co-mentor junior scientists – PhD students and MSc students.

Required background and skills of the candidate:

  • recent or pending PhD in relevant field, preferably computer science or bioinformatics;
  • at least one first-author research publication in a peer-reviewed scientific journal, top conference or currently in press (e.g. Neuroimage, Nature Methods, Nature Communications, Nature Scientific Reports, PloS, IEEE TMI, …);
  • excellent written and oral English communication skills;
  • excellent programming skills.

We offer a fixed term contract for 40 hours per week until the end of 2023. This will be supported by an educational plan that includes attendance of courses and (international) meetings. The contract will include opportunities to participate in teaching and supervision of undergraduate and master students.

The salary, depending on relevant experience before the beginning of the employment contract, will be up to 14000 PLN gross per month, based on a full-time contract (40 hours a week) for the duration of 2 years with private medical care and a sports card.

Sano offers excellent opportunities for study and development, an access to many international conferences on computational medicine and a possibility to grow in a scientific society.

If you feel that this job opportunity is the career that you are looking for, please apply immediately and give Sano a chance to meet you. Please, be informed that Sano will contact only with Candidates fulfilling the formal criteria.

Sano is an equal-opportunity employer. We prioritize diversity and are committed to creating an inclusive environment for everyone. We value a spirit of enquiry and perseverance, provide the space to keep asking questions, and promote a culture of curiosity and creativity.

Do you recognize yourself in the job profile? Then we look forward to receiving your application.

Applications in .pdf should include:

  • a cover letter;
  • a curriculum vitae;

Apply through Sano recruitment system. If you would like to apply for future openings feel free to send your application to our database.​