Igor Shuryak

Columbia University is seeking a postdoctoral researcher to join Professor Igor Shuryak’s group in New York City, focusing on the development of causal machine learning methods for precision oncology. The successful candidate will work on estimating treatment effects from real oncology datasets and translating these findings into clinical tools for radiation therapy. This position is part of a broader initiative to integrate causal machine learning with mechanistic radiobiology, aiming to optimize precision cancer treatment. The research will involve advanced methods such as double machine learning (DML), targeted maximum likelihood estimation (TMLE), causal forests, survival-focused learners, and emerging causal foundation models. The postdoc will have access to real clinical datasets spanning multiple cancer types, offering strong potential for high-impact publications in machine learning and medical journals. The role also includes active collaborations with leading groups in causal machine learning. This opportunity is funded by the Empire AI Fellows Program, providing access to New York State’s AI supercomputing infrastructure. The position offers a competitive salary of $72,000 per year plus benefits and is available for a two-year term. The research environment is highly interdisciplinary, situated at the Columbia University Irving Medical Center and the Mailman School of Public Health. Ideal candidates will have a strong background in causal inference and/or survival analysis, with a PhD in computer science, statistics, biomedical engineering, or a related field. Experience with machine learning, clinical data analysis, and programming is essential. The group values collaboration and research productivity, and referrals for finishing PhD students or recent graduates are welcome. To apply, candidates should submit their application via the provided Interfolio link. For more information about Professor Shuryak and his research, visit his LinkedIn profile. This is an excellent opportunity for researchers interested in the intersection of machine learning, oncology, and clinical data science.