PhD in Machine Learning and Computational Chemistry for Binding Affinity Prediction Lund University in Sweden

Doctoral student position in machine learning and computational chemistry at Lund University, in collaboration with AstraZeneca and Uppsala University.

The project focuses on binding affinity prediction for small molecules in drug design, combining physics-based methods and modern machine learning. Research topics include MM/PBSA, free-energy perturbation, SQM 2.20, fragment molecular orbital calculations, molecular modelling, quantum mechanics, statistical mechanics, and data-driven model development for prioritising drug candidates from hit discovery to lead optimisation.

The host environment is the Division of Computational Chemistry and the Computational Biochemistry group, which works across quantum chemistry, statistical mechanics, machine learning, biochemistry, medicinal chemistry, and structural biology. The project is tightly linked to Molecular AI at AstraZeneca and the Department of Pharmaceutical Biosciences at Uppsala University.

Eligibility highlights: applicants should have an MSc in computational chemistry, bioinformatics, machine learning, computer science, mathematics, statistics, physics, or a related discipline. Required skills include Python/programming, independent research ability, strong communication skills, good English, and a collaborative mindset. Preferred experience includes machine learning for scientific problems, molecular dynamics, molecular mechanics, quantum mechanics, binding affinity prediction, HPC, workflow tools, automation, and collaborative software development.

This is a full-time fixed-term doctoral studentship starting 2026-09-01 or as agreed. The employment is for 4 years full time, with extension possible for teaching and departmental duties. The post is based in Lund, Sweden.

Application materials must be in English and include a CV, cover letter, degree/study certificates, and any additional supporting documents such as transcripts, references, or recommendation letters. Deadline: 2026-04-26.