Senior Data Science Analyst

Union:  Non-Union Number of Vacancies:  1 New or Replacement Position:  New Site:  MaRS Department:  Research Reports to:  Senior Scientist Salary Range: $78,954 - $118,424 Per Year Hours:  37.5 hours per week Shifts:  Day Shifts Status:  Permanent Full-time Closing Date: October 30, 2026  Position Summary : We seek a talented and driven Data Scientist passionate about accelerating drug discovery through machine learning and AI to join our team at the Structural Genomics Consortium (SGC). As a Data Scientist at SGC, you will play a central role in developing and deploying state-of-the-art machine learning models that extract actionable insights from complex biomedical datasets, including DNA-Encoded Library (DEL) screens, to identify and optimize drug candidates for challenging protein targets. Your work will directly contribute to our mission of open science and pre-competitive drug discovery. The candidate will be assisted by software developers to leverage internal tools ( AIRCHECK ) in order to develop, train and test machine learning (ML) and artificial intelligence (AI) predictive models, independently or in collaboration with other experts in the Haibe-Kains and Schapira labs and other SGC collaborators. Duties • Design, build, and deploy end-to-end machine learning pipelines, from raw data ingestion and preprocessing through model training, evaluation, and production deployment. • Develop and apply predictive models to DEL screening data and other high-dimensional biomedical datasets to prioritize drug-like compounds for defined protein targets. • Implement and fine-tune deep learning architectures (transformers, graph neural networks, generative models) for molecular property prediction and de novo drug design. • Perform rigorous exploratory data analysis, statistical modelling, and visualization to surface meaningful patterns in large, noisy biomedical datasets. • Establish and maintain MLOps best practices, including model versioning, pipeline automation, experiment tracking, and reproducible workflows. • Collaborate closely with structural biologists, medicinal chemists, and bioinformaticians to translate scientific questions into robust machine learning solutions. • Present findings, methodologies, and model performance clearly to both technical collaborators and non-technical stakeholders. • Stay current with the latest advances in ML/AI for drug discovery and proactively evaluate and integrate novel approaches into the team’s research workflows. • Bachelor’s, Master’s or higher degree in Computer Science, Data Science, Bioinformatics, Computational Chemistry, or a related field. • Masters’ with 4 years related experience. • Bachelor’s degree with 6 years related experience • Proven experience designing and implementing machine learning models, particularly in drug discovery or biomedical domains. • Strong expertise in developing end-to-end ML pipelines, from data preprocessing to model deployment, using Python and related libraries (e.g., scikit-learn, pandas, NumPy). • Hands-on experience working with DNA-Encoded Library (DEL) data or similar complex, high-dimensional biomedical datasets. • Familiarity with MLOps practices, including model versioning, pipeline automation, and reproducible workflows (e.g., MLflow, Airflow). • Proficiency in deep learning frameworks such as TensorFlow, PyTorch, or Keras, with experience building transformers, graph neural networks, or generative models. • Deep understanding of feature extraction, model evaluation metrics, and optimization techniques for noisy biomedical data. • Demonstrated ability to perform exploratory data analysis, statistical modelling, and data visualization for large datasets. • Experience collaborating within multidisciplinary te