Major accountabilities:

• Leading projects and effectively communicating with stakeholders and collaborators.
• Actively participating in the design and development of clinical pipeline and customization of pooling trial data as needed to address important scientific questions, such as indication expansion.
• Independently designing, using, and improving bioinformatics tools and models that are specifically designed for integrating different types of data, enabling the exploration of various biological layers.
• Acting as a connector between valuable data resources and project teams, enhancing the generation of hypotheses by sharing insights derived from or applied to late-stage pipeline data.

Essential Requirements:

• Preferably PhD in quantitative field such as computer science, data science, mathematics, statistics, or physics. Experience working on problems in the life sciences is a plus.
• At least 2 years of professional experience in the pharmaceutical or clinical sector.
• Experience in at least one of the following: - Using biostatistics methods for inference and hypothesis testing, such as linear and logistic regression or Cox proportional hazard models, and leveraging clinical data for secondary analysis. - Track record of applying AI / deep learning to scientific data. - Experience in using machine learning models to predict clinical endpoints using multimodal data.
• Experience with Python and R scientific stacks, track record of building custom scientific software using best practices (version control, testing, documentation).
• Ability to work as part of an intercultural and interdisciplinary team, including biologists, chemists, and data scientists. Strong communication skills in verbal, written, and virtual formats.

Nice to have:

• Hands-on expertise and a proven track record in utilizing patient/clinical data to generate actionable hypotheses.
• Knowledge of computer programing language SPARK and Experience in using Foundry for data analysis.
• Published research in machine learning conferences such as ICML, ICLR, NeurIPS, or comparable venues