Doctoral Researcher in Probabilistic Machine Learning

Doctoral Researcher in Probabilistic Machine Learning

We are now looking for a:

Doctoral Researcher

We are looking for a doctoral researcher(PhD student) with a strong background in probabilistic machine learning, statistics, applied mathematics, computer science, or a related field, and strong programming skills, to work on biology-informed machine learning for dynamical systems (see project description below). The position is based at the Department of Computer Science at Aalto University, Finland, within a research environment spanning the Computational Systems Biology group, the Finnish Centre for Artificial Intelligence (FCAI), and ELLIS Institute Finland. You will be supervised by Dr Julien Martinelli and Associate Professor Harri Lähdesmäki. The position offers a broad local research network in Bayesian machine learning and computational biology.

Your network and team

Dr Martinelli is an independent Research Fellow supported by an Academy Research Fellowship of the Research Council of Finland and develops Biology-Informed Machine Learning methods for biomedical applications. Associate Professor Lähdesmäki leads Aalto’s Computational Systems Biology group and has extensive expertise in Bayesian inference for biological systems.

Project description

Ordinary differential equation (ODE) models provide interpretable descriptions of biological processes, but they are often incomplete: mechanisms may be only partly known, data are noisy and sparsely sampled, measurements vary across individuals and conditions, and some relevant biological states are unobserved. Purely data-driven models offer flexibility, but often ignore known biology and provide limited insight into uncertainty and mechanisms. These challenges motivate a broader Biology-Informed Machine Learning perspective [1].

The doctoral student’s thesis will focus on operationalising this perspective through the development of Biology-Informed Gaussian Processes (BioGPs). These are Bayesian dynamical models that combine known mechanistic components with flexible Gaussian process terms representing unknown or misspecified biology. Depending on the candidate’s interests, there may also be opportunities to connect this research with emerging foundation-model approaches for dynamical systems [2]. Key methodological questions shared across these directions include reliable uncertainty quantification, inference from heterogeneous trajectories, partial observability, and the integration of uncertain prior knowledge. A central goal will also be to go beyond trajectory prediction by coupling these approaches with methods for learning explicit, interpretable mechanistic ODEs, including their symbolic structure [3]. Lastly, recent work from the team includes nonparametric mixed-effect ODE models for population- and subject-specific dynamics [4], as well as GP-based approaches to modelling temporal single-cell data [5].

Selected references

[1] J. Martinelli. “Position: Biology is the Challenge Physics-Informed ML Needs to Evolve”. In: Advances in Neural Information Processing Systems. Vol. 38. . 2025.

[2] J. R. Hübers et al. “Foundation Inference Models for Ordinary Differential Equations”. In: . 2026.

[3] C. Métayer, A. Ballesta, and J. Martinelli. “Data-driven discovery of digital twins in biomedical research”. In: 27.1 (2026), bbaf722.

[4] J. Martinelli et al. Bayesian Nonparametric Mixed-Effect ODEs with Gaussian Processes. 2026.

[5] M. Y. Balik and H. Lähdesmäki. “Modeling Temporal scRNA-seq Data with Latent Gaussian Process and Optimal Transport”. In: Proceedings of the 43rd International Conference on Machine Learning. . 2026.

What we offer

The position belongs to the Aalto career system and the selected person will be appointed for a two-year fixed term appointment with an option for two-year renewal.

The starting salary for the position is 3168,20 EUR per month. In addition to the salary, the contract includes occupational health benefits, and Finland has a comprehensive social security system. The annual total workload of research and teaching staff at Aalto University is 1 612 hours. The position is located at the Aalto University Otaniemi campus.