Research Scientist (x/f/m)

Set a new pulse for healthcare!

We are looking for a Research Scientist to join the Doctolab team (Doctolib Clinical AI Research Lab).

Your mission is to build accurate, well-calibrated, and clinically reliable models of patient health, learned from health data at scale. The work is both fundamental and applied: you publish, and your models reach products used by doctors and patients. Doctolib is used by around 450,000 health professionals and 90 million people across Europe, and research that succeeds in the lab can be deployed at that scale.

Working at Doctolib means contributing to one of Europe's leading health-tech companies, and seeing your work improve care for patients and practitioners.

How we work

Doctolab is a research lab in its founding phase, so researchers have real influence over its direction and its priorities. We work closely with the data science and product teams, and we stay close to the data.

We expect researchers to explain why a question matters, not only why it is open. Projects are chosen on both scientific ambition and what they change for patients and practitioners. The work suits researchers who want to see their results used.

The questions we raise are open problems in machine learning: world models that predict the consequences of an action, calibration and uncertainty, causal inference from observational data, multimodal sequence modelling, orchestration between model capabilities. Results on these questions hold well beyond healthcare. We are in a strong position to work on them: we have the data to learn a world model from, a clinical use case that defines success, and the engineering path to put it in front of practitioners and patients and learn from what comes back. Experience with healthcare or medical data is a plus but not required. Both early-career and experienced researchers are welcome.

What you'll do

Your responsibilities include but are not limited to:

Build a world model of patient health: how a health state evolves over time and changes in response to care, learned from observational data with the confounding accounted for

Build evaluation methods that test calibration, robustness, interpretability, privacy, and generalization outside the training distribution

Work with the data science and product teams to turn research results into clinical-grade features

Publish at leading machine learning and health informatics venues

Engage the international health and machine learning community through open collaboration: data challenges, shared benchmarks, and open-source releases

Help define the lab's research agenda and its working relationship with the rest of the company

Who you are

Before you read on: if you don't have the exact profile described below, but you feel this job description matches your skill set, we still encourage you to apply.

You'll be a great fit if you:

Have a PhD in machine learning, statistics, computer science, or a related field, or a Master's degree with significant research experience

Have depth in one or more of: representation learning and self-supervised learning; large language models and multimodal modelling; causal inference and causal discovery from observational data; temporal and dynamic modelling; calibration and uncertainty quantification; agentic systems and orchestration; evaluation and benchmarking; privacy auditing of machine learning models

Have first-author publications at leading venues such as NeurIPS, ICML, ICLR, ACL, EMNLP, or comparable medical informatics venues

Have driven your own research, from choosing the question to publishing the result

Are proficient in Python and a deep learning framework such as PyTorch, and have trained models yourself