About the Role
We at the Mass General Brigham NeuroAI Center are seeking a highly motivated Postdoctoral Research Fellow with expertise in machine learning (ML) and biomedical data analysis to contribute to cutting-edge research at the intersection of neuroscience, critical care, and computational modeling. This position will focus on developing advanced AI/ML models for prediction and outcome assessment in acute neurological conditions, leveraging EEG, EHR, telemetry, and neuroimaging data.
This is a full-time and in-person position.
WHAT WE OFFER:
- A dynamic, interdisciplinary research environment at the forefront of AI in neuroscience and critical care.
- Access to large-scale clinical datasets and state-of-the-art computational resources
- Opportunities to publish in top-tier journals and present at leading conferences.
- A collaborative and intellectually stimulating research team with strong clinical and computational expertise.
HOW TO APPLY:
Interested candidates should submit a single PDF file including:
1. Two-page CV detailing relevant experience and publications.
2. One-page cover letter with exactly five bullet points, each no more than two lines, demonstrating your fit for this position.
3. Contact information for three references.
Applications will be reviewed on a rolling basis until the position is filled. For application submission and inquiries, please contact: mzabihi@mgh.harvard.edu
When submitting your application, please ensure the email subject line follows this format: ‘Postdoc Application – [Your Full Name]’
Join us in advancing AI-driven precision medicine and neurological prognostication!
Requirements
KEY RESPONSIBILITIES:
Develop and validate multimodal AI/ML models integrating diverse clinical and physiological data.
Design and implement time-series prediction frameworks utilizing transformer-based architectures, ensemble learning, and deep learning techniques.
Manage large-scale electronic health record (EHR), EEG, and telemetry datasets, ensuring robust preprocessing, feature extraction, and handling of missing data.
Apply explainable AI (XAI) techniques such as SHAP and attention mechanisms to enhance model interpretability.
Implement validation strategies, including nested cross-validation, conformal prediction for uncertainty quantification, and adversarial training for model robustness.
Collaborate with a multidisciplinary team of clinicians, data scientists, and engineers to refine models for real-world deployment.
Contribute to manuscript preparation, grant writing, and dissemination of research findings at leading conferences and journals.
QUALIFICATIONS:
Ph.D. in computer science, biomedical engineering, computational neuroscience, applied mathematics, or a related field.
Strong expertise in machine learning, deep learning, and statistical modeling with applications in biomedical data.
Experience with time-series analysis, transformers, LSTMs, and other temporal modeling techniques.
Proficiency in Python, PyTorch, and ML frameworks; experience with EHR data processing and feature engineering is a plus.
Familiarity with neurophysiological data (EEG, telemetry) and neuroimaging analysis is highly desirable.
Strong publication record in AI/ML applications for healthcare or neuroscience.
Excellent problem-solving skills, ability to work independently, and strong collaborative mindset.
Excellent written and oral communication skills
PREFERRED SKILLS: NOT REQUIRED
Proven ability to efficiently utilize cloud computing platforms (e.g., Azure, AWS, Google Cloud) and high-performance computing (HPC) clusters for scheduling, assigning, and managing computational research jobs.
Knowledge of self-supervised learning and domain adaptation.
Familiarity with neuroscience-related ML challenges, such as predicting clinical deterioration or integrating multimodal physiological data.
The MGH Center for Neurotechnology and Neurorecovery (CNTR) develops, tests, and deploys novel neurotechnologies to improve the care of people suffering from diseases or injuries of the nervous system.