Skip to content Skip to navigation

Open Postdoctoral position, faculty mentor Nigam Shah

Important Info

Faculty Sponsor (Last, First Name): 
Shah, Nigam
Other Mentor(s) if Applicable: 
Jason Fries
Stanford Departments and Centers: 
Biomedical Informatics
Postdoc Appointment Term: 
1 year, potentially renewable
Appointment Start Date: 
January 2023
How to Submit Application Materials: 

Please submit all application materials in one PDF document to:

Applied Machine Learning Postdoctoral Scholar: Exploring Foundation Models in Medicine
About the position: Building on our prior research in developing state-of-the-art representation learning methods for electronic health records (EHR), we are recruiting an applied postdoctoral scholar to develop computational infrastructure for training and evaluating large-scale medical foundation models. The candidate will have access to millions of patient records and include multimodal data for structured codes, clinical notes, medical imaging, and more for research use. We will explore a wide range of  topics, including but not limited to:

  • Multimodal Self-supervision
  • MLOps for Healthcare Applications
  • Evaluating Model Reliability, Usefulness, and Fairness
  • Model Adaptation and Transfer Learning
  • Robustness
  • Language Modeling
  • Natural Language Prompting

The position is embedded in a research team whose collaborations span the Human Centered AI Institute (HAI), the Center for AI in Medicine and Imaging (AIMI) and the Clinical Excellence Research Center (CERC) and is co-located with the applied data science team at Stanford Health Care providing an unparalleled opportunity to translate your research advances into better patient care.
About you: You are a hands-on team member with research experience and strong software engineering skills who looks forward to collaborating with medical doctors, statisticians and computer scientists to advance multimodal machine learning and facilitate model implementation in healthcare workflows. You will manage data and compute infrastructure to turbo-charge the research of our entire team. You are a contributor at all levels: designing methods as well as experiments to evaluate them, implementing robust code, and coordinating with our collaborators.
You will find this position to be a good fit if:

  • You are passionate about improving health care
  • One of your missions in life is to improve research through solid technical infrastructure
  • You are excited to work with rich, sometimes messy, patient-level data
  • You thrive in dynamic, fast-paced environments

You look forward to responsibilities that include:

  • Developing and evaluating methods for multimodal machine learning using the health care data of millions of patients
  • Creating and maintaining shared datasets for methods benchmarking
  • Iteratively developing code to enable rapid prototyping and evaluation of ML models
  • Data wrangling including dataset cleaning and access infrastructure
  • Producing scalable, reusable code
  • Writing manuscripts and progress reports about your research
  • Working in a team of researchers

About us: We are a group of about twenty doctors, engineers, informatics professionals and students focused on enabling better care using existing health data. We develop novel methods to learn from patient-level health data including structured health encounter records, clinical notes, insurance claims, diagnostic imaging, and clinical trial data. Our primary research program is to develop and evaluate safe, ethical, and cost-effective strategies for using predictive models to guide patient care and health system workflows. Our research group is part of the Department of Medicine at Stanford.

Required Qualifications: 
  • Doctoral degree conferred prior to position start date and within the last 3 years.
  • 3+ years of experience in software design and development.
  • 2+ years of hands-on experience using Python based machine learning libraries such as scikit-learn, Tensorflow, Pytorch.
  • Strong communication skills and prior research experience required
  • Experience working in a Linux environment and being comfortable with UNIX command line tools.
  • Familiarity with productivity tools like Git, Docker.

Preferred Skills

  • Familiarity with Google Cloud Platform (GCP) services such as BigQuery
  • Prior experience working with data in the OMOP Common Data Model
Required Application Materials: 
  • Curriculum Vitae
  • Brief statement describing research interests (1-2 pages)
  • 3 letters of reference
  • Code example(s)


Stanford is an equal opportunity employer and all qualified applicants will receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, veteran status, or any other characteristic protected by law.