Principal Computational Biologist

Our client, who is the largest Pharmaceutical Company in Europe is seeking a Principal Data Scientist. We’re partnering with their Data, AI, R&D team on a groundbreaking initiative: developing foundation models trained on cellular imaging data. One of their key models is built on half a petabyte of high-resolution cell imagery, aimed at transforming how we discover treatments for cardiovascular diseases, obesity, and rare conditions. We’re looking for a principal computational biologist or data scientist to play a critical role in this project — leading the analyse of image-based embeddings, validating model outputs, and collaborating closely with ML engineers and vision scientists to ensure the biology behind the model holds up.

Must Haves:
PhD in Computational Biology, Bioinformatics, Systems Biology, or a related quantitative field.
5+ years of experience in computational biology or data science within the biotech or pharmaceutical industry.
Proven track record in target discovery, with experience progressing targets through early drug development stages.
Strong expertise in cellular imaging and high-content screening, including the analysis of microscopy images
Hands-on experience integrating and analysing multi-modal biological data, such as transcriptomics, proteomics, or single-cell data.
Proficiency in Python, including libraries such as Pandas, NumPy, scikit-learn
Experience analysing deep learning model outputs, especially from vision models and working with biological image embeddings.
Ability to evaluate model performance, interpret model outputs, and connect them to biological hypotheses.
Demonstrated ability to drive independent analysis, design evaluation frameworks, and make data-driven recommendations in an R&D context.

Plusses:
Experience working with foundation models or self-supervised learning techniques applied to biological or image data.
Familiarity with deep learning frameworks (e.g., PyTorch or TensorFlow).
Familiarity with cell-level microscopy (e.g., Cell Painting, HCS) and downstream biological interpretation.
Understanding of model feedback loops — such as collaborating with ML teams to refine models based on biological relevance.
Strong grasp of data visualization tools and techniques for communicating multi-dimensional biological findings.
Excellent communication skills, especially in translating ML/AI outputs into biological insight and decision-making.