Staff Data Scientist (Graph ML)

About the role

Join Valo Health as a Staff Data Scientist specializing in Graph ML. In this role, you will develop and deploy graph ML solutions to extract novel insights from Valo data, driving biological hypothesis generation. You will collaborate with data scientists and biologists, communicate key results to stakeholders, and work on improving Valo's integrated graph platform. The ideal candidate has deep technical expertise in graph machine learning, experience in biology research related to drug discovery, and a strong background in Python and machine learning frameworks. Key missions: Développer et déployer des solutions de machine learning sur graphes pour synthétiser et extraire des informations novatrices à partir des données de Valo.. Collaborer avec une équipe diversifiée de scientifiques des données et de biologistes pour contextualiser les cibles médicamenteuses prédites.. Diriger la conception, la mise en œuvre et l'application d'approches de machine learning sur graphes et de biologie des réseaux pour la découverte de cibles. Profile: - A successful candidate brings deep technical expertise in graph machine learning, network analytics, and modern data science best practices, along with experience in biology research in the context of drug discovery, and curiosity and excitement to learn - Advanced knowledge of and experience with graph ML techniques such as Graph Neural Network (GNN) models applied to link prediction, node classification, and other biomedical-relevant computational tasks, as well as related explainability methods - MS or PhD in a quantitative field with extensive experience at the intersection of machine learning and graph analytics - Familiarity with general graph algorithms and relevant Python libraries - Experience or general knowledge of knowledge-graph building and graph databases - Strong experience in Python and machine learning and/or deep-learning frameworks (e.g., pytorch) - Strong data visualization, analytical, problem-solving, and communication skills, with demonstrated ability to condense, summarize, and synthesize results into informative and actionable presentations to experts from different fields - Experience with data science best practices (data provenance, code versioning, reproducibility, git, etc), large-scale data analytics engines (e.g., Spark or Dask), and working in cloud environments (e.g., AWS) - Experience in healthcare, medicine, molecular biology, computational biology, or life sciences - Experience with traditional drug discovery and development processes and approaches - Domain expertise in neuroscience, immunology, and/or cardio-metabolic biology - Knowledge of related data science domains, including statistical genetics, multi-omics & real-world evidence