Research Associate/Bioinformatician in Basel

Research Associate/Bioinformatician

IOB - Institute of Molecular and Clinical Ophthalmology Basel

Basel, Switzerland

We are looking for a Research Associate/Bioinformatician to lead the quantitative analysis of retinal imaging datasets. You will work with high-dimensional representations learned from retinal images, develop longitudinal models of disease progression, and build data-driven approaches for patient stratification and clinically relevant outcome prediction. The position sits at the intersection of computational biology, medical image analysis, and translational ophthalmology.

Your responsibilities

• Analyze large-scale retinal imaging datasets (e.g. OCT, fundus photography) using deep-learning-derived imaging features;
• Develop and validate statistical and machine learning models of disease progression;
• Build patient stratification and phenotyping pipelines;
• Collaborate with clinicians to translate computational findings into clinical trial design, patient selection criteria, and endpoint development;
• Contribute to the group's publication output and present findings at international conferences.

Requirements

Minimum qualifications

• MSc or PhD in computational biology, bioinformatics, computer science, biomedical engineering, physics, statistics, or a related quantitative field;
• Strong Python programming skills and experience developing reproducible data-analysis workflows;
• Experience working with complex, high-dimensional biomedical or imaging datasets, including data quality control and validation;
• Ability to explain technical methods and results clearly to both computational and clinical collaborators;
• Evidence of independent quantitative research, such as a thesis, publication, preprint, software project, or substantial analytical contribution.

Preferred qualifications

• Experience with medical image analysis, retinal imaging, or ophthalmic data;
• Experience with survival analysis frameworks, mixed-effects modeling, or Bayesian approaches to disease progression;
• Experience with representation learning and generative or temporal modelling in learned representation spaces, for example using diffusion models, latent-variable models, or neural state-space models;
• Experience with statistical modelling or machine learning applied to longitudinal, repeated-measures, or time-to-event data;
• Experience with high-dimensional data analysis (e.g. embeddings, single-cell, or omics data), including dimensionality reduction, clustering, and phenotyping.

#J-18808-Ljbffr