Research Fellow
About The Position
The Research Fellow will work on an ongoing project to create, test, and validate AI methods that help clinicians detect false outputs generated by multimodal AI models. The current research focus is applying mechanistic interpretability techniques in the natural language domain, including large language models (LLMs). The fellow will work collaboratively with computer scientists and clinicians to support the design, coordination, execution, and analysis of domain-expert clinician annotations and assessments of mechanistic interpretability methods in clinical medicine. The research group, the Multi-Modal AI in Neuroimaging (MMAIN) Lab, is a multidisciplinary, multi-institutional collaboration among faculty at Mass General Brigham, Northeastern University’s Khoury College of Computer Science, and Dana-Farber Cancer Institute. The fellowship is fully funded for one year and includes research and career mentorship from clinician and AI faculty at Harvard-affiliated institutions. The fellow will be exposed to state-of-the-art multimodal AI and LLM interpretability research, with opportunities to publish in high-impact journals and present at national and international meetings. The experience is intended to provide a foundation for future residency, fellowship, physician-scientist, or industry careers in clinical AI. This is an onsite position at 15 Francis Street. Applicants should email a CV, cover letter describing research interests and goals, and a full publication list to hiring manager Kizzy Scott. The posting states that applications submitted only through Workday will not be forwarded to the hiring manager and may not be reviewed.
Requirements
- MD or equivalent degree and/or experience in clinical medical practice, such as internship, residency, or fellowship training, is highly desirable.
- Medical students with appropriate clinical experience and candidates with other educational backgrounds and clinical experience are encouraged to apply.
- No computer science, data science, or coding background is required; training and close collaboration with AI researchers will be provided.
- Applicants must email a CV, a cover letter describing research interests and goals, and a full list of publications to the hiring manager; Workday-only applications may not be reviewed.
Nice To Haves
- Clinical medical practice experience, including internship, residency, or fellowship training.
- An MD or equivalent degree.
Responsibilities
- Collaborate with computer scientists and clinicians on research into methods for detecting false outputs from multimodal AI models.
- Assist in designing, coordinating, and carrying out domain-expert clinician annotations and assessments of mechanistic interpretability methods in clinical medicine.
- Analyze clinician annotations and assessments.
- Contribute to research on mechanistic interpretability techniques in natural language models, including LLMs.
Benefits
- Fully funded one-year fellowship.
- Research and career mentorship from clinician and AI faculty at Harvard-affiliated institutions.
- Opportunities to publish in high-impact journals and present at national and international meetings.
- Exposure to state-of-the-art multimodal AI and LLM interpretability research.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Entry Level
Education Level
No Education Listed
