Post-Doctoral Research Fellow - Laryngology AI

The Postdoctoral Fellow will support and help lead a multidisciplinary research initiative focused on advancing laryngology through real-time machine learning, computer vision, and quantitative analysis of laryngoscopy videos. This role will involve developing, testing, validating, and translating algorithms that track laryngeal anatomy, classify examination states, extract clinically meaningful video-derived metrics, and support future clinical decision-support tools. The fellow will work with laryngologists, clinical research staff, engineers, and collaborators at Mass Eye and Ear and Mass General Brigham to move the project from proof-of-concept research toward reproducible, clinically useful deployment. This position is best suited for a highly independent, technically strong researcher with broad computer science or machine learning expertise who is interested in applying advanced AI methods to important clinical problems in laryngology.

ESSENTIAL FUNCTIONS

Data Collection & Processing Extract, curate, and manage clinical research datasets, including flexible laryngoscopy videos, frame-level annotations, laryngeal keypoint data, high-fidelity voice recordings, operative data, patient-reported outcomes, and relevant clinical metadata. Develop and maintain reproducible pipelines for video ingestion, annotation, quality control, de-identification, preprocessing, dataset versioning, and secure data management. Work with clinicians and research staff to standardize video and outcomes data collection protocols across clinic, operating room, and follow-up settings. Research & Analysis Develop and refine deep learning, computer vision, and benchmark algorithms for real-time laryngeal structure tracking, examination-state classification, anatomic feature detection, lesion or abnormality localization, and quantitative laryngoscopy. Apply supervised, self-supervised, temporal, explainable and multimodal machine learning methods to clinical video and related datasets, with rigorous evaluation of model accuracy, generalizability, latency, robustness, and clinical interpretability. Translate model outputs into clinically meaningful metrics and visualization tools that can support research, standardized examination quality, documentation, and eventual clinical decision support. Publication & Dissemination Lead and contribute to manuscripts on AI applications in laryngology, quantitative laryngoscopy, real-time video analysis, clinical validation, and related patient outcomes research. Prepare abstracts, posters, oral presentations, technical reports, grant materials, and documentation for scientific meetings, collaborators, and potential translational partners. Clinical & Translational Research Support Collaborate closely with laryngologists, research assistants, engineers, and clinical teams to test algorithms against real clinical workflows and to identify failure modes, usability needs, and implementation barriers. Participate in translational activities including clinical validation planning, regulatory and data-governance discussions, intellectual property development, and interactions with internal and external collaborators. General Research Support Maintain research codebases, model documentation, databases, and analytic workflows in accordance with institutional research ethics, HIPAA, data security, and reproducibility standards. Attend team meetings, provide regular project updates, coordinate technical priorities, contribute to grant writing, and help define milestones for continued development of the laryngoscopy AI platform. Mentor junior staff, students, and research assistants in data annotation, computational methods, experimental design, coding practices, and scientific communication.

EDUCATION AND EXPERIENCE

PhD or equivalent degree in computer science, biomedical engineering, electrical engineering, computational neuroscience, data science, statistics or a closely related field. Strong experience with modern machine learning methods, including deep learning, neural network architecture design, computer vision, video analysis, temporal modeling, supervised and/or self-supervised learning, and rigorous model evaluation strategies. Advanced programming skills in Python are required; experience with PyTorch and/or TensorFlow/Keras, OpenCV, Git, Linux/Unix environments, high-performance or cloud-based computing platforms with GPU acceleration, and reproducible research workflows is strongly preferred. Experience with DeepLabCut software is also appreciated. Excellent verbal and written communication skills, strong publication record or evidence of scholarly productivity, ability to work independently, and interest in collaborating with clinicians to translate AI research into healthcare applications. Pay Range: $70,000.00 - $71,750.00/Annual Massachusetts Eye and Ear Infirmary is an Equal Opportunity Employer. By embracing diverse skills, perspectives and ideas, we choose to lead. All qualified applicants will receive consideration for employment without regard to race, color, religious creed, national origin, sex, age, gender identity, disability, sexual orientation, military service, genetic information, and/or other status protected under law. We will ensure that all individuals with a disability are provided a reasonable accommodation to participate in the job application or interview process, to perform essential job functions, and to receive other benefits and privileges of employment. #J-18808-Ljbffr Massachusetts Eye and Ear Infirmary - MEI