Postdoctoral Fellow - Translational Molecular Pathology

Overview

Fully funded full-time postdoctoral fellow positions are available in Dr. Andrew H. Song's lab (opened in Jan. 2026) at the Department of Translational Molecular Pathology and the Institute for Data Science in Oncology, the University of Texas MD Anderson Cancer Center. We are seeking highly talented and motivated computational postdoctoral fellows with a strong background in computer science, statistics, mathematics, and bioinformatics with a passion for solving critical healthcare problems at truly large scale.

Fellows will be mentored under close guidance from a PI with a strong track record of publishing in top-tier journals (Cell, Nature Medicine, Nature Cancer, Nature Reviews Bioengineering) and ML conferences (ICML, CVPR, NeurIPS, MICCAI). This position offers an outstanding platform to grow your scientific independence, publish at the highest levels, and build a career making transformative impact in medicine.

In addition, this is a great chance to help shape an emerging computational lab in one of the world s leading cancer centers. Dr. Song's lab is dedicated to building next-generation AI tools for computational pathology, grounded in rigorous principles of statistical inference, with the overarching goal of deciphering multi-scale oncologic complexity and improving outcome prediction for cancer patients. The lab s research will focus on developing state-of-the-art foundation models and agentic AI frameworks capable of integrating diverse data modalities—including tissue images, spatial transcriptomics, spatial proteomics, and clinical reports—across multiple dimensions of clinical data (2D, 3D, and even 4D longitudinal datasets).

By combining these innovations with advanced statistical approaches such as Bayesian inference, the lab aims to open new frontiers in computational pathology and precision oncology. Based in the world s leading cancer center within the largest medical complex in the world (Texas Medical Center), candidates will have direct access to one of the most comprehensive patient tissue and data repositories anywhere.

In addition to the vibrant and rich cancer research ecosystem within TMC/Houston, candidates will have exciting opportunities to collaborate extensively with external collaborators in academia (Harvard Medical School, Stanford, and numerous leading hospitals in Asia/Europe) as well as industrial partners to foster translational impact  Anderson also provides a wealth of computational resources, including high-performance computing clusters tailored for biomedical research and on-demand access to the Texas Advanced Computing Center.

For more information, refer to Dr. Song s website at

All duties and responsibilities are carried out in compliance with institutional policies, ethical research standards, and applicable federal and state regulations.

Learn and master skills for in-depth profiling and distillation/fusion of heterogeneous multimodal high-dimensional data sources (tissue images and transcriptomics/proteomics/metabolomics data). Gain extensive experience on developing and applying state-of-the-art AI frameworks in vision/language/omics. In addition to these research skills, the candidate will be trained heavily on efficient and clear communication with collaborators in clinical settings, mentoring junior trainees, publishing high-impact articles, and writing grants for career development.

Candidates with a Ph.D. in Computer Science, Electrical Engineering, Statistics, Mathematics, Biomedical data sciences or a related field are encouraged to apply.

• Strong computational skills
• Proficient in python and pytorch with extensive experience of training/validating AI models (computer vision and LLM).
• Extensive experience in handling and analyzing tissue image data (H&E whole-slide images) and/or omics data (bulk-seq, spatial omics data)
• Experience in large-scale, high-performance GPU cluster training and job handling
• Experience with open-source codebases (Github, Hugging Face) and engagement with the developer community
• Strong publication background
• Proven track record of journal publications (or…