Postdoctoral Research Scientist

The Center for Radiological Research at Columbia University Irving Medical Center seeks a highly motivated postdoctoral researcher to develop and apply cutting-edge causal machine learning methods for precision radiotherapy optimization. This position is funded through the prestigious Empire AI Fellows Program, New York State's initiative to advance computational research using the Empire AI computing infrastructure. Empire AI is a unique consortium of public and private research institutions advancing AI research for the public good.

The candidate will work at the intersection of causal inference, machine learning, and clinical oncology, developing methods to estimate treatment effects from multimodal observational medical data and translating these methods into clinical decision support tools.

Research Focus

The postdoc will lead projects in:

• Causal Machine Learning: Implementing and extending state-of-the-art methods including Double Machine Learning (DML), Targeted Maximum Likelihood Estimation (TMLE), causal forests, and causal foundation models for treatment effect estimation
• Multimodal Data Integration: Combining tabular, imaging, and text data for precision medicine applications
• Clinical Translation: Collaborating with radiation oncologists, radiation biologists, causal inference experts, data scientists and medical physicists to deploy causal ML models in clinical workflows

Application Domain: Radiotherapy optimization for cancer treatment, with focus on head and neck cancer, lung cancer, pancreatic cancer and other solid tumors

Key Responsibilities

• Design and implement causal machine learning algorithms for treatment effect estimation at population and subgroup/individual patient levels
• Analyze large-scale clinical datasets (electronic health records, cancer registries, clinical trial data)
• Integrate mechanistic radiobiological models with data-driven causal ML approaches
• Develop clinical decision support tools in collaboration with physicians and AI engineers
• Publish research findings in top-tier machine learning conferences (NeurIPS, ICML) and medical journals
• Present work at national/international conferences
• Collaborate with external partners including University of Texas Medical Branch and leading causal ML researchers in Europe
• Contribute to grant applications

What We Offer

• World-class research environment at Columbia University Irving Medical Center
• Access to Empire AI computing infrastructure - New York State's cutting-edge AI supercomputing resources
• Rich clinical datasets including multi-institutional cancer registries and clinical trial data
• Collaborative research network with leading causal ML researchers (LMU Munich, University of Hamburg) and clinical partners (UT Medical Branch)
• Professional development through Empire AI Fellows Program including networking opportunities, workshops, and mentorship
• Publication support for high-impact venues in both ML and medical domains
• Career advancement with strong track record of mentees securing faculty and industry positions
• New York City location with vibrant AI/ML research community

About the Research Group

The Center for Radiological Research is a world-renowned research center with over 100 years of history studying radiation effects and cancer biology and oncology. Our group combines mechanistic modeling, data science, and clinical collaboration to advance precision radiotherapy. We maintain active collaborations with leading medical AI centers and active federal funding (NIH, NASA, DoD).

Principal Investigator: Dr. Igor Shuryak (MD, PhD) - Associate Professor of Radiation Oncology with 135+ publications in radiation biology, mathematical modeling, and causal machine learning. Recent work includes methods accepted at NeurIPS 2025 and collaborations with leading causal inference researchers.

Required Qualifications

• PhD in Computer Science, Statistics, Biostatistics, Computational Biology, Machine Learning, or related quantitative field (must be completed by start date)
• Strong background in at least two of: causal inference, machine learning, statistical modeling, survival analysis
• Proficiency in Python and R and relevant ML/statistical libraries (PyTorch/TensorFlow, scikit-learn, grf, etc.)
• Experience analyzing real-world datasets and handling messy/incomplete data
• Strong scientific writing and communication skills

Preferred Qualifications

• Experience with causal inference methods (propensity scores, doubly robust estimation, etc.)
• Familiarity with survival analysis and censored data
• Experience with deep learning and/or foundation models
• Knowledge of high-performance computing environments
• Prior experience with multimodal data (imaging, text, structured data)

Columbia University is an Equal Opportunity Employer / Disability / Veteran

Pay Transparency Disclosure

The salary of the finalist selected for this role will be set based on a variety of factors, including but not limited to departmental budgets, qualifications, experience, education, licenses, specialty, and training. The above hiring range represents the University's good faith and reasonable estimate of the range of possible compensation at the time of posting.