Share job

We seek passionate and highly motivated interns for the Biomolecular Emulator (BioEmu) project. The BioEmu project aims to model the dynamics and function of proteins --- how they change shape, bind to each other, and bind small molecules. This approach will help us to understand biological function and dysfunction on a structural level and lead to more effective and targeted drug discovery. Our BioEmu-1 model was published in Science (see our blog post for links to our open-source software and other resources, as well as this explainer video).

Intern Duration: 12 Weeks

Locations: Berlin, Germany Or Cambridge, UK

Required/Minimum Qualifications:

• Advanced degree or current PhD enrollment in machine learning, AI, Physics, Chemistry, biophysics, structural biology, or a related field.
• Hands‑on experience developing machine learning models.
• Proficiency in collaborative Python development on shared research codebases.
• Strong communication skills to work effectively in an interdisciplinary team and explain technical concepts to collaborators from diverse backgrounds.

Preferred/Additional Qualifications:

• Experience working with and evaluating models such as AlphaFold and Boltz.
• Experience with diffusion models (training, sampling, evaluation).
• Experience designing and producing large‑scale datasets for ML (e.g., curating structural biology or biophysical datasets, establishing data quality criteria, and building scalable loaders).

• Design and implement machine learning models to capture protein structure, dynamics, and interactions; run ablation studies and baselines to validate ideas.
• Curate and build datasets (e.g., structural/biophysical data) and develop robust data pipelines suitable for large‑scale training and evaluation.
• Define and refine evaluation metrics/benchmarks where none exist; analyze failure modes and quantify uncertainty.
• Contribute high‑quality research code in shared Python codebases (e.g., PyTorch/NumPy/SciPy/Pandas), emphasizing reproducibility and clarity.
• Collaborate across disciplines (machine learning, structural biology, biophysics); communicate results clearly to diverse collaborators; present findings in group forums.
• Aim for impact: help translate research artifacts (models, datasets, papers, blog posts) for broader community use.