We are continuously looking for outstanding postdoctoral researchers, doctoral students, MSc students, and interns (it is often possible to arrange funding, even though we currently wouldn't have any call open). Before contacting me about any employment opportunities please first read the text below!

What do we do? - the big picture

While our main "application area" is often motivated by atmospheric processes described below, the machine learning / artificial intelligence (ML/AI) research we do is generic and published on quality ML/AI journals and conferences. Examples of fundamental ML/AI topics covered are: probabilistic emulator / predictive regression models for atmospheric processes, randomisation methods for interactive visual data exploration, advanced statistical methods for ML/AI, and explainable AI.

We work in multidisciplinary team of computer and atmospheric scientists. We are currently setting up our new Virtual Laboratory for Molecular Level Atmospheric Transformations (VILMA) Centre of Excellence. The objective of VILMA is to model atmospheric molecular level processes efficiently and to understand the underlying mechanisms and causal connections. VILMA will combine first-principles quantum chemical and other simulations and probabilistic ML/AI models with interactive visualisation and exploratory data analysis.

Who can we hire?

The persons we hire should advance the AI/ML research agenda described above. Interest in the atmospheric science topics described above is considerd an advantage, but not an absolute requirement; in fact, most of our work is  "AI/ML theory" that is in no way specific to atmospheric topics but which often can be applied there as well.

The duration of the contract for doctoral students and postdoctoral researchers is agreed individually; the total duration of PhD studies is typically 4 years and postdoctoral contracts are typically between 1 and 4 years. We welcome PhD students and postdoctoral researchers both from Finland and abroad.

Interns and MSc students - who have, e.g., done well in my classes - will work on research-grade problems that tie in with our scientific interests. The contract will be agreed individually. Depending on phase of studies typical options are (i) 3 month full-time internship project (often, but not necessarily, as summer internship) or a part-time internship (which makes it possible to do some courses at the same time, typical arrangement for students during teaching periods) that by mutual agreement can later continue to MSc or even PhD thesis; or (ii) 6 month MSc thesis project that by mutual agreement can later continue to PhD thesis. The intern and MSc student applicants should have a study right in a Finnish university; we encourage interested students from outside Finland to apply first to the relevant Bachelor's Programme or Master's Programme (e.g., data science, theoretical and computational methods, or atmospheric sciences) at the University of Helsinki.

Any candidate should have basic knowledge of ML and related mathematics and some programming skills. We will consider applicants with backgrounds in computer science, mathematics, atmospheric science, physics, and chemistry. Interest in natural sciences is considered an advantage. Prior knowledge of atmospheric processes is not required.

How to contact us?

If you are interested in working with us then please send Kai Puolamäki by email a brief motivation letter (typically max. 1 page) where you explain why you would like to work with us and what are your main interest with respect to ML/AI. Please attach to your email a copy of your study transcript that clearly displays the grades and what their maximums are (an unofficial copy is ok) if you are interested in a student position or CV (that includes a list of publications) if you are interested in a postdoctoral researcher position. I will basically consider the following three items when looking at your email: (i) skills and experience  (demonstrated, e.g., by course grades for a student candidate or publications for postdoctoral researcher candidate), (ii) topical fit (your skills and experience are relevant for our research agenda), and (iii) motivation to work with us and interest in our research topics. You can also attach other documents (such as names of references, portfolio of your past work etc.), but these are not typically necessary for the first contact. We will be in touch with you if there is an opening.

Examples of topics: ML/AI with real world data

Below, you can find some of the topics that we are actively working on:

  1. Explainable AI for digital twins. We use machine learning algorithms together with physics simulators to model atmospheric transformations, measurement devices, and other processes. We call these models collectively "digital twins". In this project the task is to apply methods, developed, e.g., in our prior work to find useful an understandable explanations for these digital twins. As a starting point you can use Björklund et al. (2019),  Puolamäki et al. (2020), and/or Björklund et al. (2022).
  2. Uncertainty quantification for AI. In almost any real-world application of machine learning (atmospheric transformations included) concept drift is an issue, meaning that a model trained in some circumstances (e.g., under specific environment, for specific molecules etc.) may not work in other circumstances. The detection and quantification of concept drift is crucial: can we trust the outputs of our models? The other way to put it is that we want to be able to find confidence intervals for machine learning models (if the confidence intervals are wide then there is concept drift and vice versa). In this project you can use Oikarinen et al. (2021) as a starting point. This problem is closely related to active learning: how to choose the training data in order to reduce the uncertainties most?
  3. Open-source tools for randomization and exploratory data analysis. Visual exploration of high-dimensional datasets and in the future of digital twins is a fundamental task in exploratory data analysis (EDA). We have developed a theoretical model for EDA, where patterns already identified and considered known by the user are input as knowledge to the exploration system. The user is shown views of the data where the user’s knowledge has been taken into account. In this project you will implement an open-source tool for exploratory data analysis. The tool should be web-based, cross-platform, and scale to large datasets. Programming skills and previous experience of open-source software development are considered an advantage.